Hugging Face's logo

bcacdwk
/
slidesparse-checkpoints

Safetensors
slidesparse
sparse
quantization
int8
fp8
llama
qwen
Model card Files
xet
Community
slidesparse-checkpoints / BitNet-2B-INT8 /conversion_report.json
bcacdwk's picture
bcacdwk
Upload BitNet-2B-INT8
94773db verified
raw
history blame contribute delete
136 kB
 {
"input_dir": "/root/vllmbench/checkpoints/BitNet-2B-BF16",
"output_dir": "/root/vllmbench/checkpoints_slidesparse/BitNet-2B-BF16-SlideSparse-2_2",
"config": {
"Z": 2,
"L": 2,
"N": 1,
"window_size": 4,
"stride": 2,
"num_windows": 0,
"expand_ratio": 0.0,
"in_group_size": 2,
"out_group_size": 0
},
"mode": "magnitude",
"skip_prune": false,
"skip_slide": true,
"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,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15199788411458334
}
]
}
},
{
"key": "model.layers.0.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17113432707609955
}
]
}
},
{
"key": "model.layers.0.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16855446144386574
}
]
}
},
{
"key": "model.layers.0.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.256956787109375
}
]
}
},
{
"key": "model.layers.0.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2794976806640625
}
]
}
},
{
"key": "model.layers.0.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.30107269287109373
}
]
}
},
{
"key": "model.layers.0.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1873193359375
}
]
}
},
{
"key": "model.layers.1.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.3483530680338542
}
]
}
},
{
"key": "model.layers.1.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.48345709906684026
}
]
}
},
{
"key": "model.layers.1.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.48394843207465277
}
]
}
},
{
"key": "model.layers.1.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.189381103515625
}
]
}
},
{
"key": "model.layers.1.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.22034423828125
}
]
}
},
{
"key": "model.layers.1.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2115972900390625
}
]
}
},
{
"key": "model.layers.1.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.181151123046875
}
]
}
},
{
"key": "model.layers.10.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17935282389322918
}
]
}
},
{
"key": "model.layers.10.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18504457826967594
}
]
}
},
{
"key": "model.layers.10.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1506580494068287
}
]
}
},
{
"key": "model.layers.10.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.3022802734375
}
]
}
},
{
"key": "model.layers.10.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1412506103515625
}
]
}
},
{
"key": "model.layers.10.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.278251953125
}
]
}
},
{
"key": "model.layers.10.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.176573486328125
}
]
}
},
{
"key": "model.layers.11.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.14923502604166666
}
]
}
},
{
"key": "model.layers.11.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.176190185546875
}
]
}
},
{
"key": "model.layers.11.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16084493001302083
}
]
}
},
{
"key": "model.layers.11.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.242635498046875
}
]
}
},
{
"key": "model.layers.11.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.128812255859375
}
]
}
},
{
"key": "model.layers.11.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2742071533203125
}
]
}
},
{
"key": "model.layers.11.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.160145263671875
}
]
}
},
{
"key": "model.layers.12.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1784042923538773
}
]
}
},
{
"key": "model.layers.12.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18707829228153935
}
]
}
},
{
"key": "model.layers.12.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.167960046838831
}
]
}
},
{
"key": "model.layers.12.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.28708740234375
}
]
}
},
{
"key": "model.layers.12.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17186126708984376
}
]
}
},
{
"key": "model.layers.12.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2387982177734375
}
]
}
},
{
"key": "model.layers.12.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16762939453125
}
]
}
},
{
"key": "model.layers.13.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17230473271122684
}
]
}
},
{
"key": "model.layers.13.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18391441062644676
}
]
}
},
{
"key": "model.layers.13.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.14585254810474538
}
]
}
},
{
"key": "model.layers.13.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.228272705078125
}
]
}
},
{
"key": "model.layers.13.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1856365966796875
}
]
}
},
{
"key": "model.layers.13.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.21499114990234375
}
]
}
},
{
"key": "model.layers.13.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.172703857421875
}
]
}
},
{
"key": "model.layers.14.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19432203504774306
}
]
}
},
{
"key": "model.layers.14.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19343894675925927
}
]
}
},
{
"key": "model.layers.14.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16939380787037037
}
]
}
},
{
"key": "model.layers.14.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.3281884765625
}
]
}
},
{
"key": "model.layers.14.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16054779052734375
}
]
}
},
{
"key": "model.layers.14.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.277701416015625
}
]
}
},
{
"key": "model.layers.14.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.11505859375
}
]
}
},
{
"key": "model.layers.15.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1797210693359375
}
]
}
},
{
"key": "model.layers.15.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19692936650028936
}
]
}
},
{
"key": "model.layers.15.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17652644404658566
}
]
}
},
{
"key": "model.layers.15.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15416015625
}
]
}
},
{
"key": "model.layers.15.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.12657806396484375
}
]
}
},
{
"key": "model.layers.15.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2110638427734375
}
]
}
},
{
"key": "model.layers.15.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.091549072265625
}
]
}
},
{
"key": "model.layers.16.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18986194751880786
}
]
}
},
{
"key": "model.layers.16.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15843031141493055
}
]
}
},
{
"key": "model.layers.16.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17178627296730323
}
]
}
},
{
"key": "model.layers.16.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.218714599609375
}
]
}
},
{
"key": "model.layers.16.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18352264404296875
}
]
}
},
{
"key": "model.layers.16.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.23088409423828124
}
]
}
},
{
"key": "model.layers.16.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1065673828125
}
]
}
},
{
"key": "model.layers.17.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.14451587818287037
}
]
}
},
{
"key": "model.layers.17.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19717282895688656
}
]
}
},
{
"key": "model.layers.17.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16488783094618056
}
]
}
},
{
"key": "model.layers.17.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.31508544921875
}
]
}
},
{
"key": "model.layers.17.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1187261962890625
}
]
}
},
{
"key": "model.layers.17.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2463275146484375
}
]
}
},
{
"key": "model.layers.17.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20371337890625
}
]
}
},
{
"key": "model.layers.18.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16681428132233797
}
]
}
},
{
"key": "model.layers.18.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1786736382378472
}
]
}
},
{
"key": "model.layers.18.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15566112377025462
}
]
}
},
{
"key": "model.layers.18.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.213857421875
}
]
}
},
{
"key": "model.layers.18.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20393035888671876
}
]
}
},
{
"key": "model.layers.18.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2262286376953125
}
]
}
},
{
"key": "model.layers.18.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.09686279296875
}
]
}
},
{
"key": "model.layers.19.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1752655029296875
}
]
}
},
{
"key": "model.layers.19.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.166396642614294
}
]
}
},
{
"key": "model.layers.19.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.204178308557581
}
]
}
},
{
"key": "model.layers.19.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17760009765625
}
]
}
},
{
"key": "model.layers.19.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.12464263916015625
}
]
}
},
{
"key": "model.layers.19.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19770599365234376
}
]
}
},
{
"key": "model.layers.19.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.122510986328125
}
]
}
},
{
"key": "model.layers.2.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2550498679832176
}
]
}
},
{
"key": "model.layers.2.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.3559205231843171
}
]
}
},
{
"key": "model.layers.2.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.3575468840422454
}
]
}
},
{
"key": "model.layers.2.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15003173828125
}
]
}
},
{
"key": "model.layers.2.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20570770263671875
}
]
}
},
{
"key": "model.layers.2.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18801513671875
}
]
}
},
{
"key": "model.layers.2.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.150972900390625
}
]
}
},
{
"key": "model.layers.20.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18525673195167824
}
]
}
},
{
"key": "model.layers.20.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1829010009765625
}
]
}
},
{
"key": "model.layers.20.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19712739167390048
}
]
}
},
{
"key": "model.layers.20.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.319686279296875
}
]
}
},
{
"key": "model.layers.20.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18260040283203124
}
]
}
},
{
"key": "model.layers.20.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2580020141601562
}
]
}
},
{
"key": "model.layers.20.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.154796142578125
}
]
}
},
{
"key": "model.layers.21.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.14428337944878472
}
]
}
},
{
"key": "model.layers.21.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17313514992042825
}
]
}
},
{
"key": "model.layers.21.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15726759168836807
}
]
}
},
{
"key": "model.layers.21.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.219298095703125
}
]
}
},
{
"key": "model.layers.21.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20331451416015625
}
]
}
},
{
"key": "model.layers.21.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.25748626708984373
}
]
}
},
{
"key": "model.layers.21.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.155692138671875
}
]
}
},
{
"key": "model.layers.22.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17556468822337962
}
]
}
},
{
"key": "model.layers.22.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18298170301649305
}
]
}
},
{
"key": "model.layers.22.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15903331615306712
}
]
}
},
{
"key": "model.layers.22.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.229600830078125
}
]
}
},
{
"key": "model.layers.22.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20516082763671875
}
]
}
},
{
"key": "model.layers.22.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.22682281494140624
}
]
}
},
{
"key": "model.layers.22.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1089990234375
}
]
}
},
{
"key": "model.layers.23.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16933186848958334
}
]
}
},
{
"key": "model.layers.23.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15015417028356481
}
]
}
},
{
"key": "model.layers.23.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15995099103009258
}
]
}
},
{
"key": "model.layers.23.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2611669921875
}
]
}
},
{
"key": "model.layers.23.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15424041748046874
}
]
}
},
{
"key": "model.layers.23.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.25669921875
}
]
}
},
{
"key": "model.layers.23.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.150548095703125
}
]
}
},
{
"key": "model.layers.24.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15282999674479167
}
]
}
},
{
"key": "model.layers.24.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17266212745949075
}
]
}
},
{
"key": "model.layers.24.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17506759078414352
}
]
}
},
{
"key": "model.layers.24.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.270911865234375
}
]
}
},
{
"key": "model.layers.24.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17739471435546875
}
]
}
},
{
"key": "model.layers.24.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.26747161865234376
}
]
}
},
{
"key": "model.layers.24.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.176749267578125
}
]
}
},
{
"key": "model.layers.25.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16077451352719907
}
]
}
},
{
"key": "model.layers.25.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15167134602864582
}
]
}
},
{
"key": "model.layers.25.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16715630425347222
}
]
}
},
{
"key": "model.layers.25.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.177279052734375
}
]
}
},
{
"key": "model.layers.25.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18887603759765625
}
]
}
},
{
"key": "model.layers.25.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2086029052734375
}
]
}
},
{
"key": "model.layers.25.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.12677978515625
}
]
}
},
{
"key": "model.layers.26.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.13425281665943287
}
]
}
},
{
"key": "model.layers.26.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15587825068721065
}
]
}
},
{
"key": "model.layers.26.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18711694788049768
}
]
}
},
{
"key": "model.layers.26.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.188653564453125
}
]
}
},
{
"key": "model.layers.26.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1992559814453125
}
]
}
},
{
"key": "model.layers.26.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.21903289794921876
}
]
}
},
{
"key": "model.layers.26.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.137728271484375
}
]
}
},
{
"key": "model.layers.27.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1363655372902199
}
]
}
},
{
"key": "model.layers.27.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2003430401837384
}
]
}
},
{
"key": "model.layers.27.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19456154152199073
}
]
}
},
{
"key": "model.layers.27.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.22201171875
}
]
}
},
{
"key": "model.layers.27.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1796588134765625
}
]
}
},
{
"key": "model.layers.27.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2278948974609375
}
]
}
},
{
"key": "model.layers.27.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1123095703125
}
]
}
},
{
"key": "model.layers.28.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16350075050636573
}
]
}
},
{
"key": "model.layers.28.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1676529495804398
}
]
}
},
{
"key": "model.layers.28.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1866291187427662
}
]
}
},
{
"key": "model.layers.28.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.183768310546875
}
]
}
},
{
"key": "model.layers.28.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19795166015625
}
]
}
},
{
"key": "model.layers.28.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18107330322265625
}
]
}
},
{
"key": "model.layers.28.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15234619140625
}
]
}
},
{
"key": "model.layers.29.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16791845251012733
}
]
}
},
{
"key": "model.layers.29.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20634200484664353
}
]
}
},
{
"key": "model.layers.29.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17300256799768518
}
]
}
},
{
"key": "model.layers.29.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16551025390625
}
]
}
},
{
"key": "model.layers.29.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.3195074462890625
}
]
}
},
{
"key": "model.layers.29.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1834649658203125
}
]
}
},
{
"key": "model.layers.29.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.247176513671875
}
]
}
},
{
"key": "model.layers.3.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.21333380805121527
}
]
}
},
{
"key": "model.layers.3.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2500740333839699
}
]
}
},
{
"key": "model.layers.3.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2590979682074653
}
]
}
},
{
"key": "model.layers.3.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.173878173828125
}
]
}
},
{
"key": "model.layers.3.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18900421142578125
}
]
}
},
{
"key": "model.layers.3.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20758697509765625
}
]
}
},
{
"key": "model.layers.3.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.152174072265625
}
]
}
},
{
"key": "model.layers.4.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.17481248643663194
}
]
}
},
{
"key": "model.layers.4.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2107018364800347
}
]
}
},
{
"key": "model.layers.4.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2166152388961227
}
]
}
},
{
"key": "model.layers.4.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.198648681640625
}
]
}
},
{
"key": "model.layers.4.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1776983642578125
}
]
}
},
{
"key": "model.layers.4.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.21193206787109375
}
]
}
},
{
"key": "model.layers.4.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.142794189453125
}
]
}
},
{
"key": "model.layers.5.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18577213993778935
}
]
}
},
{
"key": "model.layers.5.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1812286376953125
}
]
}
},
{
"key": "model.layers.5.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18417573151765046
}
]
}
},
{
"key": "model.layers.5.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.234036865234375
}
]
}
},
{
"key": "model.layers.5.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.20351898193359375
}
]
}
},
{
"key": "model.layers.5.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2208203125
}
]
}
},
{
"key": "model.layers.5.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15800537109375
}
]
}
},
{
"key": "model.layers.6.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1422286422164352
}
]
}
},
{
"key": "model.layers.6.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18378974066840278
}
]
}
},
{
"key": "model.layers.6.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.18515082465277777
}
]
}
},
{
"key": "model.layers.6.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.19806640625
}
]
}
},
{
"key": "model.layers.6.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.155452880859375
}
]
}
},
{
"key": "model.layers.6.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.25316802978515623
}
]
}
},
{
"key": "model.layers.6.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.12183837890625
}
]
}
},
{
"key": "model.layers.7.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.14323628743489583
}
]
}
},
{
"key": "model.layers.7.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16950107150607638
}
]
}
},
{
"key": "model.layers.7.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1680545383029514
}
]
}
},
{
"key": "model.layers.7.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.202620849609375
}
]
}
},
{
"key": "model.layers.7.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16763763427734374
}
]
}
},
{
"key": "model.layers.7.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.22835784912109375
}
]
}
},
{
"key": "model.layers.7.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.130732421875
}
]
}
},
{
"key": "model.layers.8.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1428402370876736
}
]
}
},
{
"key": "model.layers.8.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.16652662489149306
}
]
}
},
{
"key": "model.layers.8.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1641455756293403
}
]
}
},
{
"key": "model.layers.8.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.23819091796875
}
]
}
},
{
"key": "model.layers.8.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1687322998046875
}
]
}
},
{
"key": "model.layers.8.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.25700439453125
}
]
}
},
{
"key": "model.layers.8.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.12066162109375
}
]
}
},
{
"key": "model.layers.9.mlp.down_proj.weight",
"result": {
"original_shape": [
2560,
6912
],
"final_shape": [
2560,
6912
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
6912
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1411677607783565
}
]
}
},
{
"key": "model.layers.9.mlp.gate_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1797061496310764
}
]
}
},
{
"key": "model.layers.9.mlp.up_proj.weight",
"result": {
"original_shape": [
6912,
2560
],
"final_shape": [
6912,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
6912,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.15515894006799769
}
]
}
},
{
"key": "model.layers.9.self_attn.k_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.2318359375
}
]
}
},
{
"key": "model.layers.9.self_attn.o_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1947369384765625
}
]
}
},
{
"key": "model.layers.9.self_attn.q_proj.weight",
"result": {
"original_shape": [
2560,
2560
],
"final_shape": [
2560,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
2560,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.1998541259765625
}
]
}
},
{
"key": "model.layers.9.self_attn.v_proj.weight",
"result": {
"original_shape": [
640,
2560
],
"final_shape": [
640,
2560
],
"stages": [
{
"name": "quant_prune",
"shape": [
640,
2560
],
"output_dtype": "int8",
"ZL_valid": false,
"ZL_valid_ratio": 0.124481201171875
}
]
}
}
],
"skipped": [
"model.embed_tokens.weight",
"model.layers.0.input_layernorm.weight",
"model.layers.0.mlp.ffn_sub_norm.weight",
"model.layers.0.post_attention_layernorm.weight",
"model.layers.0.self_attn.attn_sub_norm.weight",
"model.layers.1.input_layernorm.weight",
"model.layers.1.mlp.ffn_sub_norm.weight",
"model.layers.1.post_attention_layernorm.weight",
"model.layers.1.self_attn.attn_sub_norm.weight",
"model.layers.10.input_layernorm.weight",
"model.layers.10.mlp.ffn_sub_norm.weight",
"model.layers.10.post_attention_layernorm.weight",
"model.layers.10.self_attn.attn_sub_norm.weight",
"model.layers.11.input_layernorm.weight",
"model.layers.11.mlp.ffn_sub_norm.weight",
"model.layers.11.post_attention_layernorm.weight",
"model.layers.11.self_attn.attn_sub_norm.weight",
"model.layers.12.input_layernorm.weight",
"model.layers.12.mlp.ffn_sub_norm.weight",
"model.layers.12.post_attention_layernorm.weight",
"model.layers.12.self_attn.attn_sub_norm.weight",
"model.layers.13.input_layernorm.weight",
"model.layers.13.mlp.ffn_sub_norm.weight",
"model.layers.13.post_attention_layernorm.weight",
"model.layers.13.self_attn.attn_sub_norm.weight",
"model.layers.14.input_layernorm.weight",
"model.layers.14.mlp.ffn_sub_norm.weight",
"model.layers.14.post_attention_layernorm.weight",
"model.layers.14.self_attn.attn_sub_norm.weight",
"model.layers.15.input_layernorm.weight",
"model.layers.15.mlp.ffn_sub_norm.weight",
"model.layers.15.post_attention_layernorm.weight",
"model.layers.15.self_attn.attn_sub_norm.weight",
"model.layers.16.input_layernorm.weight",
"model.layers.16.mlp.ffn_sub_norm.weight",
"model.layers.16.post_attention_layernorm.weight",
"model.layers.16.self_attn.attn_sub_norm.weight",
"model.layers.17.input_layernorm.weight",
"model.layers.17.mlp.ffn_sub_norm.weight",
"model.layers.17.post_attention_layernorm.weight",
"model.layers.17.self_attn.attn_sub_norm.weight",
"model.layers.18.input_layernorm.weight",
"model.layers.18.mlp.ffn_sub_norm.weight",
"model.layers.18.post_attention_layernorm.weight",
"model.layers.18.self_attn.attn_sub_norm.weight",
"model.layers.19.input_layernorm.weight",
"model.layers.19.mlp.ffn_sub_norm.weight",
"model.layers.19.post_attention_layernorm.weight",
"model.layers.19.self_attn.attn_sub_norm.weight",
"model.layers.2.input_layernorm.weight",
"model.layers.2.mlp.ffn_sub_norm.weight",
"model.layers.2.post_attention_layernorm.weight",
"model.layers.2.self_attn.attn_sub_norm.weight",
"model.layers.20.input_layernorm.weight",
"model.layers.20.mlp.ffn_sub_norm.weight",
"model.layers.20.post_attention_layernorm.weight",
"model.layers.20.self_attn.attn_sub_norm.weight",
"model.layers.21.input_layernorm.weight",
"model.layers.21.mlp.ffn_sub_norm.weight",
"model.layers.21.post_attention_layernorm.weight",
"model.layers.21.self_attn.attn_sub_norm.weight",
"model.layers.22.input_layernorm.weight",
"model.layers.22.mlp.ffn_sub_norm.weight",
"model.layers.22.post_attention_layernorm.weight",
"model.layers.22.self_attn.attn_sub_norm.weight",
"model.layers.23.input_layernorm.weight",
"model.layers.23.mlp.ffn_sub_norm.weight",
"model.layers.23.post_attention_layernorm.weight",
"model.layers.23.self_attn.attn_sub_norm.weight",
"model.layers.24.input_layernorm.weight",
"model.layers.24.mlp.ffn_sub_norm.weight",
"model.layers.24.post_attention_layernorm.weight",
"model.layers.24.self_attn.attn_sub_norm.weight",
"model.layers.25.input_layernorm.weight",
"model.layers.25.mlp.ffn_sub_norm.weight",
"model.layers.25.post_attention_layernorm.weight",
"model.layers.25.self_attn.attn_sub_norm.weight",
"model.layers.26.input_layernorm.weight",
"model.layers.26.mlp.ffn_sub_norm.weight",
"model.layers.26.post_attention_layernorm.weight",
"model.layers.26.self_attn.attn_sub_norm.weight",
"model.layers.27.input_layernorm.weight",
"model.layers.27.mlp.ffn_sub_norm.weight",
"model.layers.27.post_attention_layernorm.weight",
"model.layers.27.self_attn.attn_sub_norm.weight",
"model.layers.28.input_layernorm.weight",
"model.layers.28.mlp.ffn_sub_norm.weight",
"model.layers.28.post_attention_layernorm.weight",
"model.layers.28.self_attn.attn_sub_norm.weight",
"model.layers.29.input_layernorm.weight",
"model.layers.29.mlp.ffn_sub_norm.weight",
"model.layers.29.post_attention_layernorm.weight",
"model.layers.29.self_attn.attn_sub_norm.weight",
"model.layers.3.input_layernorm.weight",
"model.layers.3.mlp.ffn_sub_norm.weight",
"model.layers.3.post_attention_layernorm.weight",
"model.layers.3.self_attn.attn_sub_norm.weight",
"model.layers.4.input_layernorm.weight",
"model.layers.4.mlp.ffn_sub_norm.weight",
"model.layers.4.post_attention_layernorm.weight",
"model.layers.4.self_attn.attn_sub_norm.weight",
"model.layers.5.input_layernorm.weight",
"model.layers.5.mlp.ffn_sub_norm.weight",
"model.layers.5.post_attention_layernorm.weight",
"model.layers.5.self_attn.attn_sub_norm.weight",
"model.layers.6.input_layernorm.weight",
"model.layers.6.mlp.ffn_sub_norm.weight",
"model.layers.6.post_attention_layernorm.weight",
"model.layers.6.self_attn.attn_sub_norm.weight",
"model.layers.7.input_layernorm.weight",
"model.layers.7.mlp.ffn_sub_norm.weight",
"model.layers.7.post_attention_layernorm.weight",
"model.layers.7.self_attn.attn_sub_norm.weight",
"model.layers.8.input_layernorm.weight",
"model.layers.8.mlp.ffn_sub_norm.weight",
"model.layers.8.post_attention_layernorm.weight",
"model.layers.8.self_attn.attn_sub_norm.weight",
"model.layers.9.input_layernorm.weight",
"model.layers.9.mlp.ffn_sub_norm.weight",
"model.layers.9.post_attention_layernorm.weight",
"model.layers.9.self_attn.attn_sub_norm.weight",
"model.norm.weight"
]
}
],
"total_layers_processed": 210,
"total_layers_skipped": 122,
"elapsed_time": 8.408682823181152
}