diff --git "a/Qwen2.5-7B-INT8-SlideSparse-2_10/conversion_report.json" "b/Qwen2.5-7B-INT8-SlideSparse-2_10/conversion_report.json" new file mode 100644--- /dev/null +++ "b/Qwen2.5-7B-INT8-SlideSparse-2_10/conversion_report.json" @@ -0,0 +1,10178 @@ +{ + "input_dir": "/root/vllmbench/checkpoints/Qwen2.5-7B-INT8", + "output_dir": "/root/vllmbench/checkpoints_slidesparse/Qwen2.5-7B-INT8-SlideSparse-2_10", + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + }, + "mode": "magnitude", + "skip_prune": false, + "skip_slide": false, + "skip_compress": true, + "use_real_cusparselt": true, + "files": [ + { + "file": "model-00001-of-00002.safetensors", + "layers": [ + { + "key": "model.layers.0.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.0.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.0.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.0.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.0.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.0.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.0.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.1.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.10.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.11.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.12.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.13.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.14.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.15.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.16.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.16.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.16.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.16.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.16.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.16.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.2.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.3.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.4.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.5.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.6.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.7.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.8.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.9.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + } + ], + "skipped": [ + "model.embed_tokens.weight", + "model.layers.0.input_layernorm.weight", + "model.layers.0.mlp.down_proj.weight_scale", + "model.layers.0.mlp.gate_proj.weight_scale", + "model.layers.0.mlp.up_proj.weight_scale", + "model.layers.0.post_attention_layernorm.weight", + "model.layers.0.self_attn.k_proj.bias", + "model.layers.0.self_attn.k_proj.weight_scale", + "model.layers.0.self_attn.o_proj.weight_scale", + "model.layers.0.self_attn.q_proj.bias", + "model.layers.0.self_attn.q_proj.weight_scale", + "model.layers.0.self_attn.v_proj.bias", + "model.layers.0.self_attn.v_proj.weight_scale", + "model.layers.1.input_layernorm.weight", + "model.layers.1.mlp.down_proj.weight_scale", + "model.layers.1.mlp.gate_proj.weight_scale", + "model.layers.1.mlp.up_proj.weight_scale", + "model.layers.1.post_attention_layernorm.weight", + "model.layers.1.self_attn.k_proj.bias", + "model.layers.1.self_attn.k_proj.weight_scale", + "model.layers.1.self_attn.o_proj.weight_scale", + "model.layers.1.self_attn.q_proj.bias", + "model.layers.1.self_attn.q_proj.weight_scale", + "model.layers.1.self_attn.v_proj.bias", + "model.layers.1.self_attn.v_proj.weight_scale", + "model.layers.10.input_layernorm.weight", + "model.layers.10.mlp.down_proj.weight_scale", + "model.layers.10.mlp.gate_proj.weight_scale", + "model.layers.10.mlp.up_proj.weight_scale", + "model.layers.10.post_attention_layernorm.weight", + "model.layers.10.self_attn.k_proj.bias", + "model.layers.10.self_attn.k_proj.weight_scale", + "model.layers.10.self_attn.o_proj.weight_scale", + "model.layers.10.self_attn.q_proj.bias", + "model.layers.10.self_attn.q_proj.weight_scale", + "model.layers.10.self_attn.v_proj.bias", + "model.layers.10.self_attn.v_proj.weight_scale", + "model.layers.11.input_layernorm.weight", + "model.layers.11.mlp.down_proj.weight_scale", + "model.layers.11.mlp.gate_proj.weight_scale", + "model.layers.11.mlp.up_proj.weight_scale", + "model.layers.11.post_attention_layernorm.weight", + "model.layers.11.self_attn.k_proj.bias", + "model.layers.11.self_attn.k_proj.weight_scale", + "model.layers.11.self_attn.o_proj.weight_scale", + "model.layers.11.self_attn.q_proj.bias", + "model.layers.11.self_attn.q_proj.weight_scale", + "model.layers.11.self_attn.v_proj.bias", + "model.layers.11.self_attn.v_proj.weight_scale", + "model.layers.12.input_layernorm.weight", + "model.layers.12.mlp.down_proj.weight_scale", + "model.layers.12.mlp.gate_proj.weight_scale", + "model.layers.12.mlp.up_proj.weight_scale", + "model.layers.12.post_attention_layernorm.weight", + "model.layers.12.self_attn.k_proj.bias", + "model.layers.12.self_attn.k_proj.weight_scale", + "model.layers.12.self_attn.o_proj.weight_scale", + "model.layers.12.self_attn.q_proj.bias", + "model.layers.12.self_attn.q_proj.weight_scale", + "model.layers.12.self_attn.v_proj.bias", + "model.layers.12.self_attn.v_proj.weight_scale", + "model.layers.13.input_layernorm.weight", + "model.layers.13.mlp.down_proj.weight_scale", + "model.layers.13.mlp.gate_proj.weight_scale", + "model.layers.13.mlp.up_proj.weight_scale", + "model.layers.13.post_attention_layernorm.weight", + "model.layers.13.self_attn.k_proj.bias", + "model.layers.13.self_attn.k_proj.weight_scale", + "model.layers.13.self_attn.o_proj.weight_scale", + "model.layers.13.self_attn.q_proj.bias", + "model.layers.13.self_attn.q_proj.weight_scale", + "model.layers.13.self_attn.v_proj.bias", + "model.layers.13.self_attn.v_proj.weight_scale", + "model.layers.14.input_layernorm.weight", + "model.layers.14.mlp.down_proj.weight_scale", + "model.layers.14.mlp.gate_proj.weight_scale", + "model.layers.14.mlp.up_proj.weight_scale", + "model.layers.14.post_attention_layernorm.weight", + "model.layers.14.self_attn.k_proj.bias", + "model.layers.14.self_attn.k_proj.weight_scale", + "model.layers.14.self_attn.o_proj.weight_scale", + "model.layers.14.self_attn.q_proj.bias", + "model.layers.14.self_attn.q_proj.weight_scale", + "model.layers.14.self_attn.v_proj.bias", + "model.layers.14.self_attn.v_proj.weight_scale", + "model.layers.15.input_layernorm.weight", + "model.layers.15.mlp.down_proj.weight_scale", + "model.layers.15.mlp.gate_proj.weight_scale", + "model.layers.15.mlp.up_proj.weight_scale", + "model.layers.15.post_attention_layernorm.weight", + "model.layers.15.self_attn.k_proj.bias", + "model.layers.15.self_attn.k_proj.weight_scale", + "model.layers.15.self_attn.o_proj.weight_scale", + "model.layers.15.self_attn.q_proj.bias", + "model.layers.15.self_attn.q_proj.weight_scale", + "model.layers.15.self_attn.v_proj.bias", + "model.layers.15.self_attn.v_proj.weight_scale", + "model.layers.16.mlp.gate_proj.weight_scale", + "model.layers.16.mlp.up_proj.weight_scale", + "model.layers.16.self_attn.k_proj.bias", + "model.layers.16.self_attn.k_proj.weight_scale", + "model.layers.16.self_attn.o_proj.weight_scale", + "model.layers.16.self_attn.q_proj.bias", + "model.layers.16.self_attn.q_proj.weight_scale", + "model.layers.16.self_attn.v_proj.bias", + "model.layers.16.self_attn.v_proj.weight_scale", + "model.layers.2.input_layernorm.weight", + "model.layers.2.mlp.down_proj.weight_scale", + "model.layers.2.mlp.gate_proj.weight_scale", + "model.layers.2.mlp.up_proj.weight_scale", + "model.layers.2.post_attention_layernorm.weight", + "model.layers.2.self_attn.k_proj.bias", + "model.layers.2.self_attn.k_proj.weight_scale", + "model.layers.2.self_attn.o_proj.weight_scale", + "model.layers.2.self_attn.q_proj.bias", + "model.layers.2.self_attn.q_proj.weight_scale", + "model.layers.2.self_attn.v_proj.bias", + "model.layers.2.self_attn.v_proj.weight_scale", + "model.layers.3.input_layernorm.weight", + "model.layers.3.mlp.down_proj.weight_scale", + "model.layers.3.mlp.gate_proj.weight_scale", + "model.layers.3.mlp.up_proj.weight_scale", + "model.layers.3.post_attention_layernorm.weight", + "model.layers.3.self_attn.k_proj.bias", + "model.layers.3.self_attn.k_proj.weight_scale", + "model.layers.3.self_attn.o_proj.weight_scale", + "model.layers.3.self_attn.q_proj.bias", + "model.layers.3.self_attn.q_proj.weight_scale", + "model.layers.3.self_attn.v_proj.bias", + "model.layers.3.self_attn.v_proj.weight_scale", + "model.layers.4.input_layernorm.weight", + "model.layers.4.mlp.down_proj.weight_scale", + "model.layers.4.mlp.gate_proj.weight_scale", + "model.layers.4.mlp.up_proj.weight_scale", + "model.layers.4.post_attention_layernorm.weight", + "model.layers.4.self_attn.k_proj.bias", + "model.layers.4.self_attn.k_proj.weight_scale", + "model.layers.4.self_attn.o_proj.weight_scale", + "model.layers.4.self_attn.q_proj.bias", + "model.layers.4.self_attn.q_proj.weight_scale", + "model.layers.4.self_attn.v_proj.bias", + "model.layers.4.self_attn.v_proj.weight_scale", + "model.layers.5.input_layernorm.weight", + "model.layers.5.mlp.down_proj.weight_scale", + "model.layers.5.mlp.gate_proj.weight_scale", + "model.layers.5.mlp.up_proj.weight_scale", + "model.layers.5.post_attention_layernorm.weight", + "model.layers.5.self_attn.k_proj.bias", + "model.layers.5.self_attn.k_proj.weight_scale", + "model.layers.5.self_attn.o_proj.weight_scale", + "model.layers.5.self_attn.q_proj.bias", + "model.layers.5.self_attn.q_proj.weight_scale", + "model.layers.5.self_attn.v_proj.bias", + "model.layers.5.self_attn.v_proj.weight_scale", + "model.layers.6.input_layernorm.weight", + "model.layers.6.mlp.down_proj.weight_scale", + "model.layers.6.mlp.gate_proj.weight_scale", + "model.layers.6.mlp.up_proj.weight_scale", + "model.layers.6.post_attention_layernorm.weight", + "model.layers.6.self_attn.k_proj.bias", + "model.layers.6.self_attn.k_proj.weight_scale", + "model.layers.6.self_attn.o_proj.weight_scale", + "model.layers.6.self_attn.q_proj.bias", + "model.layers.6.self_attn.q_proj.weight_scale", + "model.layers.6.self_attn.v_proj.bias", + "model.layers.6.self_attn.v_proj.weight_scale", + "model.layers.7.input_layernorm.weight", + "model.layers.7.mlp.down_proj.weight_scale", + "model.layers.7.mlp.gate_proj.weight_scale", + "model.layers.7.mlp.up_proj.weight_scale", + "model.layers.7.post_attention_layernorm.weight", + "model.layers.7.self_attn.k_proj.bias", + "model.layers.7.self_attn.k_proj.weight_scale", + "model.layers.7.self_attn.o_proj.weight_scale", + "model.layers.7.self_attn.q_proj.bias", + "model.layers.7.self_attn.q_proj.weight_scale", + "model.layers.7.self_attn.v_proj.bias", + "model.layers.7.self_attn.v_proj.weight_scale", + "model.layers.8.input_layernorm.weight", + "model.layers.8.mlp.down_proj.weight_scale", + "model.layers.8.mlp.gate_proj.weight_scale", + "model.layers.8.mlp.up_proj.weight_scale", + "model.layers.8.post_attention_layernorm.weight", + "model.layers.8.self_attn.k_proj.bias", + "model.layers.8.self_attn.k_proj.weight_scale", + "model.layers.8.self_attn.o_proj.weight_scale", + "model.layers.8.self_attn.q_proj.bias", + "model.layers.8.self_attn.q_proj.weight_scale", + "model.layers.8.self_attn.v_proj.bias", + "model.layers.8.self_attn.v_proj.weight_scale", + "model.layers.9.input_layernorm.weight", + "model.layers.9.mlp.down_proj.weight_scale", + "model.layers.9.mlp.gate_proj.weight_scale", + "model.layers.9.mlp.up_proj.weight_scale", + "model.layers.9.post_attention_layernorm.weight", + "model.layers.9.self_attn.k_proj.bias", + "model.layers.9.self_attn.k_proj.weight_scale", + "model.layers.9.self_attn.o_proj.weight_scale", + "model.layers.9.self_attn.q_proj.bias", + "model.layers.9.self_attn.q_proj.weight_scale", + "model.layers.9.self_attn.v_proj.bias", + "model.layers.9.self_attn.v_proj.weight_scale" + ] + }, + { + "file": "model-00002-of-00002.safetensors", + "layers": [ + { + "key": "model.layers.16.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.17.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.18.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.19.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.20.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.21.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.22.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.23.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.24.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.25.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.26.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.mlp.down_proj.weight", + "result": { + "original_shape": [ + 3584, + 18944 + ], + "final_shape": [ + 3584, + 30336 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 18944 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 30336 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 18944, + "padded_k": 18950, + "output_k": 30336, + "expand_ratio": 1.6013513513513513, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.mlp.gate_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.mlp.up_proj.weight", + "result": { + "original_shape": [ + 18944, + 3584 + ], + "final_shape": [ + 18944, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 18944, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 18944, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.self_attn.k_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.self_attn.o_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.self_attn.q_proj.weight", + "result": { + "original_shape": [ + 3584, + 3584 + ], + "final_shape": [ + 3584, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 3584, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 3584, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + }, + { + "key": "model.layers.27.self_attn.v_proj.weight", + "result": { + "original_shape": [ + 512, + 3584 + ], + "final_shape": [ + 512, + 5760 + ], + "stages": [ + { + "name": "prune", + "shape": [ + 512, + 3584 + ], + "ZL_valid": true, + "ZL_valid_ratio": 1.0 + }, + { + "name": "slide", + "shape": [ + 512, + 5760 + ], + "2to4_valid": true, + "2to4_violation_ratio": 0.0, + "slide_metadata": { + "original_k": 3584, + "padded_k": 3590, + "output_k": 5760, + "expand_ratio": 1.6071428571428572, + "config": { + "Z": 2, + "L": 10, + "N": 5, + "window_size": 4, + "stride": 2, + "num_windows": 4, + "expand_ratio": 1.6, + "in_group_size": 10, + "out_group_size": 16 + } + } + } + ] + } + } + ], + "skipped": [ + "lm_head.weight", + "model.layers.16.input_layernorm.weight", + "model.layers.16.mlp.down_proj.weight_scale", + "model.layers.16.post_attention_layernorm.weight", + "model.layers.17.input_layernorm.weight", + "model.layers.17.mlp.down_proj.weight_scale", + "model.layers.17.mlp.gate_proj.weight_scale", + "model.layers.17.mlp.up_proj.weight_scale", + "model.layers.17.post_attention_layernorm.weight", + "model.layers.17.self_attn.k_proj.bias", + "model.layers.17.self_attn.k_proj.weight_scale", + "model.layers.17.self_attn.o_proj.weight_scale", + "model.layers.17.self_attn.q_proj.bias", + "model.layers.17.self_attn.q_proj.weight_scale", + "model.layers.17.self_attn.v_proj.bias", + "model.layers.17.self_attn.v_proj.weight_scale", + "model.layers.18.input_layernorm.weight", + "model.layers.18.mlp.down_proj.weight_scale", + "model.layers.18.mlp.gate_proj.weight_scale", + "model.layers.18.mlp.up_proj.weight_scale", + "model.layers.18.post_attention_layernorm.weight", + "model.layers.18.self_attn.k_proj.bias", + "model.layers.18.self_attn.k_proj.weight_scale", + "model.layers.18.self_attn.o_proj.weight_scale", + "model.layers.18.self_attn.q_proj.bias", + "model.layers.18.self_attn.q_proj.weight_scale", + "model.layers.18.self_attn.v_proj.bias", + "model.layers.18.self_attn.v_proj.weight_scale", + "model.layers.19.input_layernorm.weight", + "model.layers.19.mlp.down_proj.weight_scale", + "model.layers.19.mlp.gate_proj.weight_scale", + "model.layers.19.mlp.up_proj.weight_scale", + "model.layers.19.post_attention_layernorm.weight", + "model.layers.19.self_attn.k_proj.bias", + "model.layers.19.self_attn.k_proj.weight_scale", + "model.layers.19.self_attn.o_proj.weight_scale", + "model.layers.19.self_attn.q_proj.bias", + "model.layers.19.self_attn.q_proj.weight_scale", + "model.layers.19.self_attn.v_proj.bias", + "model.layers.19.self_attn.v_proj.weight_scale", + "model.layers.20.input_layernorm.weight", + "model.layers.20.mlp.down_proj.weight_scale", + "model.layers.20.mlp.gate_proj.weight_scale", + "model.layers.20.mlp.up_proj.weight_scale", + "model.layers.20.post_attention_layernorm.weight", + "model.layers.20.self_attn.k_proj.bias", + "model.layers.20.self_attn.k_proj.weight_scale", + "model.layers.20.self_attn.o_proj.weight_scale", + "model.layers.20.self_attn.q_proj.bias", + "model.layers.20.self_attn.q_proj.weight_scale", + "model.layers.20.self_attn.v_proj.bias", + "model.layers.20.self_attn.v_proj.weight_scale", + "model.layers.21.input_layernorm.weight", + "model.layers.21.mlp.down_proj.weight_scale", + "model.layers.21.mlp.gate_proj.weight_scale", + "model.layers.21.mlp.up_proj.weight_scale", + "model.layers.21.post_attention_layernorm.weight", + "model.layers.21.self_attn.k_proj.bias", + "model.layers.21.self_attn.k_proj.weight_scale", + "model.layers.21.self_attn.o_proj.weight_scale", + "model.layers.21.self_attn.q_proj.bias", + "model.layers.21.self_attn.q_proj.weight_scale", + "model.layers.21.self_attn.v_proj.bias", + "model.layers.21.self_attn.v_proj.weight_scale", + "model.layers.22.input_layernorm.weight", + "model.layers.22.mlp.down_proj.weight_scale", + "model.layers.22.mlp.gate_proj.weight_scale", + "model.layers.22.mlp.up_proj.weight_scale", + "model.layers.22.post_attention_layernorm.weight", + "model.layers.22.self_attn.k_proj.bias", + "model.layers.22.self_attn.k_proj.weight_scale", + "model.layers.22.self_attn.o_proj.weight_scale", + "model.layers.22.self_attn.q_proj.bias", + "model.layers.22.self_attn.q_proj.weight_scale", + "model.layers.22.self_attn.v_proj.bias", + "model.layers.22.self_attn.v_proj.weight_scale", + "model.layers.23.input_layernorm.weight", + "model.layers.23.mlp.down_proj.weight_scale", + "model.layers.23.mlp.gate_proj.weight_scale", + "model.layers.23.mlp.up_proj.weight_scale", + "model.layers.23.post_attention_layernorm.weight", + "model.layers.23.self_attn.k_proj.bias", + "model.layers.23.self_attn.k_proj.weight_scale", + "model.layers.23.self_attn.o_proj.weight_scale", + "model.layers.23.self_attn.q_proj.bias", + "model.layers.23.self_attn.q_proj.weight_scale", + "model.layers.23.self_attn.v_proj.bias", + "model.layers.23.self_attn.v_proj.weight_scale", + "model.layers.24.input_layernorm.weight", + "model.layers.24.mlp.down_proj.weight_scale", + "model.layers.24.mlp.gate_proj.weight_scale", + "model.layers.24.mlp.up_proj.weight_scale", + "model.layers.24.post_attention_layernorm.weight", + "model.layers.24.self_attn.k_proj.bias", + "model.layers.24.self_attn.k_proj.weight_scale", + "model.layers.24.self_attn.o_proj.weight_scale", + "model.layers.24.self_attn.q_proj.bias", + "model.layers.24.self_attn.q_proj.weight_scale", + "model.layers.24.self_attn.v_proj.bias", + "model.layers.24.self_attn.v_proj.weight_scale", + "model.layers.25.input_layernorm.weight", + "model.layers.25.mlp.down_proj.weight_scale", + "model.layers.25.mlp.gate_proj.weight_scale", + "model.layers.25.mlp.up_proj.weight_scale", + "model.layers.25.post_attention_layernorm.weight", + "model.layers.25.self_attn.k_proj.bias", + "model.layers.25.self_attn.k_proj.weight_scale", + "model.layers.25.self_attn.o_proj.weight_scale", + "model.layers.25.self_attn.q_proj.bias", + "model.layers.25.self_attn.q_proj.weight_scale", + "model.layers.25.self_attn.v_proj.bias", + "model.layers.25.self_attn.v_proj.weight_scale", + "model.layers.26.input_layernorm.weight", + "model.layers.26.mlp.down_proj.weight_scale", + "model.layers.26.mlp.gate_proj.weight_scale", + "model.layers.26.mlp.up_proj.weight_scale", + "model.layers.26.post_attention_layernorm.weight", + "model.layers.26.self_attn.k_proj.bias", + "model.layers.26.self_attn.k_proj.weight_scale", + "model.layers.26.self_attn.o_proj.weight_scale", + "model.layers.26.self_attn.q_proj.bias", + "model.layers.26.self_attn.q_proj.weight_scale", + "model.layers.26.self_attn.v_proj.bias", + "model.layers.26.self_attn.v_proj.weight_scale", + "model.layers.27.input_layernorm.weight", + "model.layers.27.mlp.down_proj.weight_scale", + "model.layers.27.mlp.gate_proj.weight_scale", + "model.layers.27.mlp.up_proj.weight_scale", + "model.layers.27.post_attention_layernorm.weight", + "model.layers.27.self_attn.k_proj.bias", + "model.layers.27.self_attn.k_proj.weight_scale", + "model.layers.27.self_attn.o_proj.weight_scale", + "model.layers.27.self_attn.q_proj.bias", + "model.layers.27.self_attn.q_proj.weight_scale", + "model.layers.27.self_attn.v_proj.bias", + "model.layers.27.self_attn.v_proj.weight_scale", + "model.norm.weight" + ] + } + ], + "total_layers_processed": 196, + "total_layers_skipped": 339, + "elapsed_time": 123.60593223571777 +} \ No newline at end of file