| { |
| "input_dir": "/root/vllmbench/checkpoints/BitNet-2B-FP8", |
| "output_dir": "/root/vllmbench/checkpoints_slidesparse/BitNet-2B-FP8-SlideSparse-2_6", |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| }, |
| "mode": "magnitude", |
| "skip_prune": false, |
| "skip_slide": false, |
| "skip_compress": true, |
| "use_real_cusparselt": true, |
| "files": [ |
| { |
| "file": "model.safetensors", |
| "layers": [ |
| { |
| "key": "model.layers.0.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.0.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.0.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.0.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.0.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.0.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.0.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.1.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.10.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.11.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.12.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.13.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.14.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.15.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.16.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.17.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.18.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.19.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.2.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.20.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.21.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.22.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.23.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.24.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.25.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.26.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.27.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.28.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.29.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.3.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.4.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.5.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.6.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.7.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.8.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.mlp.down_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 6912 |
| ], |
| "final_shape": [ |
| 2560, |
| 9216 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 6912 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 9216 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 6912, |
| "padded_k": 6912, |
| "output_k": 9216, |
| "expand_ratio": 1.3333333333333333, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.mlp.gate_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.mlp.up_proj.weight", |
| "result": { |
| "original_shape": [ |
| 6912, |
| 2560 |
| ], |
| "final_shape": [ |
| 6912, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 6912, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 6912, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.self_attn.k_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.self_attn.o_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.self_attn.q_proj.weight", |
| "result": { |
| "original_shape": [ |
| 2560, |
| 2560 |
| ], |
| "final_shape": [ |
| 2560, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 2560, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 2560, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| }, |
| { |
| "key": "model.layers.9.self_attn.v_proj.weight", |
| "result": { |
| "original_shape": [ |
| 640, |
| 2560 |
| ], |
| "final_shape": [ |
| 640, |
| 3424 |
| ], |
| "stages": [ |
| { |
| "name": "prune", |
| "shape": [ |
| 640, |
| 2560 |
| ], |
| "ZL_valid": true, |
| "ZL_valid_ratio": 1.0 |
| }, |
| { |
| "name": "slide", |
| "shape": [ |
| 640, |
| 3424 |
| ], |
| "2to4_valid": true, |
| "2to4_violation_ratio": 0.0, |
| "slide_metadata": { |
| "original_k": 2560, |
| "padded_k": 2562, |
| "output_k": 3424, |
| "expand_ratio": 1.3375, |
| "config": { |
| "Z": 2, |
| "L": 6, |
| "N": 3, |
| "window_size": 4, |
| "stride": 2, |
| "num_windows": 2, |
| "expand_ratio": 1.3333333333333333, |
| "in_group_size": 6, |
| "out_group_size": 8 |
| } |
| } |
| } |
| ] |
| } |
| } |
| ], |
| "skipped": [ |
| "model.embed_tokens.weight", |
| "model.layers.0.input_layernorm.weight", |
| "model.layers.0.mlp.down_proj.weight_scale", |
| "model.layers.0.mlp.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "model.layers.15.self_attn.v_proj.weight_scale", |
| "model.layers.16.input_layernorm.weight", |
| "model.layers.16.mlp.down_proj.weight_scale", |
| "model.layers.16.mlp.ffn_sub_norm.weight", |
| "model.layers.16.mlp.gate_proj.weight_scale", |
| "model.layers.16.mlp.up_proj.weight_scale", |
| "model.layers.16.post_attention_layernorm.weight", |
| "model.layers.16.self_attn.attn_sub_norm.weight", |
| "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.weight_scale", |
| "model.layers.16.self_attn.v_proj.weight_scale", |
| "model.layers.17.input_layernorm.weight", |
| "model.layers.17.mlp.down_proj.weight_scale", |
| "model.layers.17.mlp.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "model.layers.19.self_attn.v_proj.weight_scale", |
| "model.layers.2.input_layernorm.weight", |
| "model.layers.2.mlp.down_proj.weight_scale", |
| "model.layers.2.mlp.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "model.layers.2.self_attn.v_proj.weight_scale", |
| "model.layers.20.input_layernorm.weight", |
| "model.layers.20.mlp.down_proj.weight_scale", |
| "model.layers.20.mlp.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "model.layers.27.self_attn.v_proj.weight_scale", |
| "model.layers.28.input_layernorm.weight", |
| "model.layers.28.mlp.down_proj.weight_scale", |
| "model.layers.28.mlp.ffn_sub_norm.weight", |
| "model.layers.28.mlp.gate_proj.weight_scale", |
| "model.layers.28.mlp.up_proj.weight_scale", |
| "model.layers.28.post_attention_layernorm.weight", |
| "model.layers.28.self_attn.attn_sub_norm.weight", |
| "model.layers.28.self_attn.k_proj.weight_scale", |
| "model.layers.28.self_attn.o_proj.weight_scale", |
| "model.layers.28.self_attn.q_proj.weight_scale", |
| "model.layers.28.self_attn.v_proj.weight_scale", |
| "model.layers.29.input_layernorm.weight", |
| "model.layers.29.mlp.down_proj.weight_scale", |
| "model.layers.29.mlp.ffn_sub_norm.weight", |
| "model.layers.29.mlp.gate_proj.weight_scale", |
| "model.layers.29.mlp.up_proj.weight_scale", |
| "model.layers.29.post_attention_layernorm.weight", |
| "model.layers.29.self_attn.attn_sub_norm.weight", |
| "model.layers.29.self_attn.k_proj.weight_scale", |
| "model.layers.29.self_attn.o_proj.weight_scale", |
| "model.layers.29.self_attn.q_proj.weight_scale", |
| "model.layers.29.self_attn.v_proj.weight_scale", |
| "model.layers.3.input_layernorm.weight", |
| "model.layers.3.mlp.down_proj.weight_scale", |
| "model.layers.3.mlp.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "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.ffn_sub_norm.weight", |
| "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.attn_sub_norm.weight", |
| "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.weight_scale", |
| "model.layers.9.self_attn.v_proj.weight_scale", |
| "model.norm.weight" |
| ] |
| } |
| ], |
| "total_layers_processed": 210, |
| "total_layers_skipped": 332, |
| "elapsed_time": 26.36256170272827 |
| } |