,layer_id,layer_type,param_type,shape,nparam,nnz,sparsity 5,bert.encoder.layer.0.attention.self.query,Linear,weight,"[320, 768]",245760,245760,0.0 7,bert.encoder.layer.0.attention.self.key,Linear,weight,"[320, 768]",245760,245760,0.0 9,bert.encoder.layer.0.attention.self.value,Linear,weight,"[320, 768]",245760,245760,0.0 11,bert.encoder.layer.0.attention.output.dense,Linear,weight,"[768, 320]",245760,245760,0.0 15,bert.encoder.layer.0.intermediate.dense,Linear,weight,"[185, 768]",142080,142080,0.0 17,bert.encoder.layer.0.output.dense,Linear,weight,"[768, 185]",142080,142080,0.0 21,bert.encoder.layer.1.attention.self.query,Linear,weight,"[320, 768]",245760,245760,0.0 23,bert.encoder.layer.1.attention.self.key,Linear,weight,"[320, 768]",245760,245760,0.0 25,bert.encoder.layer.1.attention.self.value,Linear,weight,"[320, 768]",245760,245760,0.0 27,bert.encoder.layer.1.attention.output.dense,Linear,weight,"[768, 320]",245760,245760,0.0 31,bert.encoder.layer.1.intermediate.dense,Linear,weight,"[315, 768]",241920,241920,0.0 33,bert.encoder.layer.1.output.dense,Linear,weight,"[768, 315]",241920,241920,0.0 37,bert.encoder.layer.2.attention.self.query,Linear,weight,"[576, 768]",442368,442368,0.0 39,bert.encoder.layer.2.attention.self.key,Linear,weight,"[576, 768]",442368,442368,0.0 41,bert.encoder.layer.2.attention.self.value,Linear,weight,"[576, 768]",442368,442368,0.0 43,bert.encoder.layer.2.attention.output.dense,Linear,weight,"[768, 576]",442368,442368,0.0 47,bert.encoder.layer.2.intermediate.dense,Linear,weight,"[339, 768]",260352,260352,0.0 49,bert.encoder.layer.2.output.dense,Linear,weight,"[768, 339]",260352,260352,0.0 53,bert.encoder.layer.3.attention.self.query,Linear,weight,"[576, 768]",442368,442368,0.0 55,bert.encoder.layer.3.attention.self.key,Linear,weight,"[576, 768]",442368,442368,0.0 57,bert.encoder.layer.3.attention.self.value,Linear,weight,"[576, 768]",442368,442368,0.0 59,bert.encoder.layer.3.attention.output.dense,Linear,weight,"[768, 576]",442368,442368,0.0 63,bert.encoder.layer.3.intermediate.dense,Linear,weight,"[368, 768]",282624,282624,0.0 65,bert.encoder.layer.3.output.dense,Linear,weight,"[768, 368]",282624,282624,0.0 69,bert.encoder.layer.4.attention.self.query,Linear,weight,"[576, 768]",442368,442368,0.0 71,bert.encoder.layer.4.attention.self.key,Linear,weight,"[576, 768]",442368,442368,0.0 73,bert.encoder.layer.4.attention.self.value,Linear,weight,"[576, 768]",442368,442368,0.0 75,bert.encoder.layer.4.attention.output.dense,Linear,weight,"[768, 576]",442368,442368,0.0 79,bert.encoder.layer.4.intermediate.dense,Linear,weight,"[386, 768]",296448,296448,0.0 81,bert.encoder.layer.4.output.dense,Linear,weight,"[768, 386]",296448,296448,0.0 85,bert.encoder.layer.5.attention.self.query,Linear,weight,"[384, 768]",294912,294912,0.0 87,bert.encoder.layer.5.attention.self.key,Linear,weight,"[384, 768]",294912,294912,0.0 89,bert.encoder.layer.5.attention.self.value,Linear,weight,"[384, 768]",294912,294912,0.0 91,bert.encoder.layer.5.attention.output.dense,Linear,weight,"[768, 384]",294912,294912,0.0 95,bert.encoder.layer.5.intermediate.dense,Linear,weight,"[336, 768]",258048,258048,0.0 97,bert.encoder.layer.5.output.dense,Linear,weight,"[768, 336]",258048,258048,0.0 101,bert.encoder.layer.6.attention.self.query,Linear,weight,"[448, 768]",344064,344064,0.0 103,bert.encoder.layer.6.attention.self.key,Linear,weight,"[448, 768]",344064,344064,0.0 105,bert.encoder.layer.6.attention.self.value,Linear,weight,"[448, 768]",344064,344064,0.0 107,bert.encoder.layer.6.attention.output.dense,Linear,weight,"[768, 448]",344064,344064,0.0 111,bert.encoder.layer.6.intermediate.dense,Linear,weight,"[280, 768]",215040,215040,0.0 113,bert.encoder.layer.6.output.dense,Linear,weight,"[768, 280]",215040,215040,0.0 117,bert.encoder.layer.7.attention.self.query,Linear,weight,"[448, 768]",344064,344064,0.0 119,bert.encoder.layer.7.attention.self.key,Linear,weight,"[448, 768]",344064,344064,0.0 121,bert.encoder.layer.7.attention.self.value,Linear,weight,"[448, 768]",344064,344064,0.0 123,bert.encoder.layer.7.attention.output.dense,Linear,weight,"[768, 448]",344064,344064,0.0 127,bert.encoder.layer.7.intermediate.dense,Linear,weight,"[211, 768]",162048,162048,0.0 129,bert.encoder.layer.7.output.dense,Linear,weight,"[768, 211]",162048,162048,0.0 133,bert.encoder.layer.8.attention.self.query,Linear,weight,"[448, 768]",344064,344064,0.0 135,bert.encoder.layer.8.attention.self.key,Linear,weight,"[448, 768]",344064,344064,0.0 137,bert.encoder.layer.8.attention.self.value,Linear,weight,"[448, 768]",344064,344064,0.0 139,bert.encoder.layer.8.attention.output.dense,Linear,weight,"[768, 448]",344064,344064,0.0 143,bert.encoder.layer.8.intermediate.dense,Linear,weight,"[108, 768]",82944,82944,0.0 145,bert.encoder.layer.8.output.dense,Linear,weight,"[768, 108]",82944,82944,0.0 149,bert.encoder.layer.9.attention.self.query,Linear,weight,"[320, 768]",245760,245760,0.0 151,bert.encoder.layer.9.attention.self.key,Linear,weight,"[320, 768]",245760,245760,0.0 153,bert.encoder.layer.9.attention.self.value,Linear,weight,"[320, 768]",245760,245760,0.0 155,bert.encoder.layer.9.attention.output.dense,Linear,weight,"[768, 320]",245760,245760,0.0 159,bert.encoder.layer.9.intermediate.dense,Linear,weight,"[53, 768]",40704,40704,5.960464477539063e-08 161,bert.encoder.layer.9.output.dense,Linear,weight,"[768, 53]",40704,40704,5.960464477539063e-08 165,bert.encoder.layer.10.attention.self.query,Linear,weight,"[384, 768]",294912,294912,0.0 167,bert.encoder.layer.10.attention.self.key,Linear,weight,"[384, 768]",294912,294912,0.0 169,bert.encoder.layer.10.attention.self.value,Linear,weight,"[384, 768]",294912,294912,0.0 171,bert.encoder.layer.10.attention.output.dense,Linear,weight,"[768, 384]",294912,294912,0.0 175,bert.encoder.layer.10.intermediate.dense,Linear,weight,"[86, 768]",66048,66048,0.0 177,bert.encoder.layer.10.output.dense,Linear,weight,"[768, 86]",66048,66048,0.0 181,bert.encoder.layer.11.attention.self.query,Linear,weight,"[384, 768]",294912,294912,0.0 183,bert.encoder.layer.11.attention.self.key,Linear,weight,"[384, 768]",294912,294912,0.0 185,bert.encoder.layer.11.attention.self.value,Linear,weight,"[384, 768]",294912,294912,0.0 187,bert.encoder.layer.11.attention.output.dense,Linear,weight,"[768, 384]",294912,294912,0.0 191,bert.encoder.layer.11.intermediate.dense,Linear,weight,"[105, 768]",80640,80640,0.0 193,bert.encoder.layer.11.output.dense,Linear,weight,"[768, 105]",80640,80640,0.0