| | layer_id | layer_type | param_type | shape | nparam | nnz | sparsity | |----:|:-------------------------------------------------|:-------------|:-------------|:-------------|---------:|---------:|------------:| | 0 | bert.embeddings.word_embeddings | Embedding | weight | [30522, 768] | 23440896 | 23440896 | 0 | | 1 | bert.embeddings.position_embeddings | Embedding | weight | [512, 768] | 393216 | 393216 | 0 | | 2 | bert.embeddings.token_type_embeddings | Embedding | weight | [2, 768] | 1536 | 1536 | 0 | | 3 | bert.embeddings.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 4 | bert.embeddings.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 5 | bert.encoder.layer.0.attention.self.query | Linear | weight | [320, 768] | 245760 | 135168 | 0.45 | | 6 | bert.encoder.layer.0.attention.self.query | Linear | bias | [320] | 320 | 256 | 0.2 | | 7 | bert.encoder.layer.0.attention.self.key | Linear | weight | [320, 768] | 245760 | 149504 | 0.391667 | | 8 | bert.encoder.layer.0.attention.self.key | Linear | bias | [320] | 320 | 256 | 0.2 | | 9 | bert.encoder.layer.0.attention.self.value | Linear | weight | [320, 768] | 245760 | 173056 | 0.295833 | | 10 | bert.encoder.layer.0.attention.self.value | Linear | bias | [320] | 320 | 256 | 0.2 | | 11 | bert.encoder.layer.0.attention.output.dense | Linear | weight | [768, 320] | 245760 | 181248 | 0.2625 | | 12 | bert.encoder.layer.0.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 13 | bert.encoder.layer.0.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 14 | bert.encoder.layer.0.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 15 | bert.encoder.layer.0.intermediate.dense | Linear | weight | [185, 768] | 142080 | 142080 | 0 | | 16 | bert.encoder.layer.0.intermediate.dense | Linear | bias | [185] | 185 | 185 | 0 | | 17 | bert.encoder.layer.0.output.dense | Linear | weight | [768, 185] | 142080 | 142080 | 0 | | 18 | bert.encoder.layer.0.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 19 | bert.encoder.layer.0.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 20 | bert.encoder.layer.0.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 21 | bert.encoder.layer.1.attention.self.query | Linear | weight | [320, 768] | 245760 | 175104 | 0.2875 | | 22 | bert.encoder.layer.1.attention.self.query | Linear | bias | [320] | 320 | 288 | 0.1 | | 23 | bert.encoder.layer.1.attention.self.key | Linear | weight | [320, 768] | 245760 | 177152 | 0.279167 | | 24 | bert.encoder.layer.1.attention.self.key | Linear | bias | [320] | 320 | 288 | 0.1 | | 25 | bert.encoder.layer.1.attention.self.value | Linear | weight | [320, 768] | 245760 | 166912 | 0.320833 | | 26 | bert.encoder.layer.1.attention.self.value | Linear | bias | [320] | 320 | 288 | 0.1 | | 27 | bert.encoder.layer.1.attention.output.dense | Linear | weight | [768, 320] | 245760 | 167936 | 0.316667 | | 28 | bert.encoder.layer.1.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 29 | bert.encoder.layer.1.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 30 | bert.encoder.layer.1.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 31 | bert.encoder.layer.1.intermediate.dense | Linear | weight | [315, 768] | 241920 | 241920 | 0 | | 32 | bert.encoder.layer.1.intermediate.dense | Linear | bias | [315] | 315 | 315 | 0 | | 33 | bert.encoder.layer.1.output.dense | Linear | weight | [768, 315] | 241920 | 241920 | 0 | | 34 | bert.encoder.layer.1.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 35 | bert.encoder.layer.1.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 36 | bert.encoder.layer.1.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 37 | bert.encoder.layer.2.attention.self.query | Linear | weight | [576, 768] | 442368 | 285696 | 0.354167 | | 38 | bert.encoder.layer.2.attention.self.query | Linear | bias | [576] | 576 | 480 | 0.166667 | | 39 | bert.encoder.layer.2.attention.self.key | Linear | weight | [576, 768] | 442368 | 297984 | 0.326389 | | 40 | bert.encoder.layer.2.attention.self.key | Linear | bias | [576] | 576 | 480 | 0.166667 | | 41 | bert.encoder.layer.2.attention.self.value | Linear | weight | [576, 768] | 442368 | 226304 | 0.488426 | | 42 | bert.encoder.layer.2.attention.self.value | Linear | bias | [576] | 576 | 384 | 0.333333 | | 43 | bert.encoder.layer.2.attention.output.dense | Linear | weight | [768, 576] | 442368 | 237568 | 0.462963 | | 44 | bert.encoder.layer.2.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 45 | bert.encoder.layer.2.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 46 | bert.encoder.layer.2.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 47 | bert.encoder.layer.2.intermediate.dense | Linear | weight | [339, 768] | 260352 | 260352 | 0 | | 48 | bert.encoder.layer.2.intermediate.dense | Linear | bias | [339] | 339 | 339 | 0 | | 49 | bert.encoder.layer.2.output.dense | Linear | weight | [768, 339] | 260352 | 260352 | 0 | | 50 | bert.encoder.layer.2.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 51 | bert.encoder.layer.2.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 52 | bert.encoder.layer.2.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 53 | bert.encoder.layer.3.attention.self.query | Linear | weight | [576, 768] | 442368 | 277504 | 0.372685 | | 54 | bert.encoder.layer.3.attention.self.query | Linear | bias | [576] | 576 | 512 | 0.111111 | | 55 | bert.encoder.layer.3.attention.self.key | Linear | weight | [576, 768] | 442368 | 303104 | 0.314815 | | 56 | bert.encoder.layer.3.attention.self.key | Linear | bias | [576] | 576 | 512 | 0.111111 | | 57 | bert.encoder.layer.3.attention.self.value | Linear | weight | [576, 768] | 442368 | 297984 | 0.326389 | | 58 | bert.encoder.layer.3.attention.self.value | Linear | bias | [576] | 576 | 512 | 0.111111 | | 59 | bert.encoder.layer.3.attention.output.dense | Linear | weight | [768, 576] | 442368 | 308224 | 0.303241 | | 60 | bert.encoder.layer.3.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 61 | bert.encoder.layer.3.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 62 | bert.encoder.layer.3.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 63 | bert.encoder.layer.3.intermediate.dense | Linear | weight | [368, 768] | 282624 | 282624 | 0 | | 64 | bert.encoder.layer.3.intermediate.dense | Linear | bias | [368] | 368 | 368 | 0 | | 65 | bert.encoder.layer.3.output.dense | Linear | weight | [768, 368] | 282624 | 282624 | 0 | | 66 | bert.encoder.layer.3.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 67 | bert.encoder.layer.3.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 68 | bert.encoder.layer.3.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 69 | bert.encoder.layer.4.attention.self.query | Linear | weight | [576, 768] | 442368 | 291840 | 0.340278 | | 70 | bert.encoder.layer.4.attention.self.query | Linear | bias | [576] | 576 | 544 | 0.0555555 | | 71 | bert.encoder.layer.4.attention.self.key | Linear | weight | [576, 768] | 442368 | 310272 | 0.298611 | | 72 | bert.encoder.layer.4.attention.self.key | Linear | bias | [576] | 576 | 544 | 0.0555555 | | 73 | bert.encoder.layer.4.attention.self.value | Linear | weight | [576, 768] | 442368 | 272384 | 0.384259 | | 74 | bert.encoder.layer.4.attention.self.value | Linear | bias | [576] | 576 | 480 | 0.166667 | | 75 | bert.encoder.layer.4.attention.output.dense | Linear | weight | [768, 576] | 442368 | 263168 | 0.405093 | | 76 | bert.encoder.layer.4.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 77 | bert.encoder.layer.4.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 78 | bert.encoder.layer.4.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 79 | bert.encoder.layer.4.intermediate.dense | Linear | weight | [386, 768] | 296448 | 296448 | 0 | | 80 | bert.encoder.layer.4.intermediate.dense | Linear | bias | [386] | 386 | 386 | 0 | | 81 | bert.encoder.layer.4.output.dense | Linear | weight | [768, 386] | 296448 | 296448 | 0 | | 82 | bert.encoder.layer.4.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 83 | bert.encoder.layer.4.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 84 | bert.encoder.layer.4.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 85 | bert.encoder.layer.5.attention.self.query | Linear | weight | [384, 768] | 294912 | 171008 | 0.420139 | | 86 | bert.encoder.layer.5.attention.self.query | Linear | bias | [384] | 384 | 352 | 0.0833333 | | 87 | bert.encoder.layer.5.attention.self.key | Linear | weight | [384, 768] | 294912 | 205824 | 0.302083 | | 88 | bert.encoder.layer.5.attention.self.key | Linear | bias | [384] | 384 | 352 | 0.0833333 | | 89 | bert.encoder.layer.5.attention.self.value | Linear | weight | [384, 768] | 294912 | 217088 | 0.263889 | | 90 | bert.encoder.layer.5.attention.self.value | Linear | bias | [384] | 384 | 384 | 0 | | 91 | bert.encoder.layer.5.attention.output.dense | Linear | weight | [768, 384] | 294912 | 223232 | 0.243056 | | 92 | bert.encoder.layer.5.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 93 | bert.encoder.layer.5.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 94 | bert.encoder.layer.5.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 95 | bert.encoder.layer.5.intermediate.dense | Linear | weight | [336, 768] | 258048 | 258048 | 0 | | 96 | bert.encoder.layer.5.intermediate.dense | Linear | bias | [336] | 336 | 336 | 0 | | 97 | bert.encoder.layer.5.output.dense | Linear | weight | [768, 336] | 258048 | 258048 | 0 | | 98 | bert.encoder.layer.5.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 99 | bert.encoder.layer.5.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 100 | bert.encoder.layer.5.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 101 | bert.encoder.layer.6.attention.self.query | Linear | weight | [448, 768] | 344064 | 192512 | 0.440476 | | 102 | bert.encoder.layer.6.attention.self.query | Linear | bias | [448] | 448 | 416 | 0.0714285 | | 103 | bert.encoder.layer.6.attention.self.key | Linear | weight | [448, 768] | 344064 | 224256 | 0.348214 | | 104 | bert.encoder.layer.6.attention.self.key | Linear | bias | [448] | 448 | 416 | 0.0714285 | | 105 | bert.encoder.layer.6.attention.self.value | Linear | weight | [448, 768] | 344064 | 209920 | 0.389881 | | 106 | bert.encoder.layer.6.attention.self.value | Linear | bias | [448] | 448 | 352 | 0.214286 | | 107 | bert.encoder.layer.6.attention.output.dense | Linear | weight | [768, 448] | 344064 | 199680 | 0.419643 | | 108 | bert.encoder.layer.6.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 109 | bert.encoder.layer.6.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 110 | bert.encoder.layer.6.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 111 | bert.encoder.layer.6.intermediate.dense | Linear | weight | [280, 768] | 215040 | 215040 | 0 | | 112 | bert.encoder.layer.6.intermediate.dense | Linear | bias | [280] | 280 | 280 | 0 | | 113 | bert.encoder.layer.6.output.dense | Linear | weight | [768, 280] | 215040 | 215040 | 0 | | 114 | bert.encoder.layer.6.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 115 | bert.encoder.layer.6.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 116 | bert.encoder.layer.6.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 117 | bert.encoder.layer.7.attention.self.query | Linear | weight | [448, 768] | 344064 | 201728 | 0.41369 | | 118 | bert.encoder.layer.7.attention.self.query | Linear | bias | [448] | 448 | 416 | 0.0714285 | | 119 | bert.encoder.layer.7.attention.self.key | Linear | weight | [448, 768] | 344064 | 237568 | 0.309524 | | 120 | bert.encoder.layer.7.attention.self.key | Linear | bias | [448] | 448 | 416 | 0.0714285 | | 121 | bert.encoder.layer.7.attention.self.value | Linear | weight | [448, 768] | 344064 | 218112 | 0.366071 | | 122 | bert.encoder.layer.7.attention.self.value | Linear | bias | [448] | 448 | 352 | 0.214286 | | 123 | bert.encoder.layer.7.attention.output.dense | Linear | weight | [768, 448] | 344064 | 202752 | 0.410714 | | 124 | bert.encoder.layer.7.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 125 | bert.encoder.layer.7.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 126 | bert.encoder.layer.7.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 127 | bert.encoder.layer.7.intermediate.dense | Linear | weight | [211, 768] | 162048 | 162048 | 0 | | 128 | bert.encoder.layer.7.intermediate.dense | Linear | bias | [211] | 211 | 211 | 0 | | 129 | bert.encoder.layer.7.output.dense | Linear | weight | [768, 211] | 162048 | 162048 | 0 | | 130 | bert.encoder.layer.7.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 131 | bert.encoder.layer.7.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 132 | bert.encoder.layer.7.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 133 | bert.encoder.layer.8.attention.self.query | Linear | weight | [448, 768] | 344064 | 186368 | 0.458333 | | 134 | bert.encoder.layer.8.attention.self.query | Linear | bias | [448] | 448 | 416 | 0.0714285 | | 135 | bert.encoder.layer.8.attention.self.key | Linear | weight | [448, 768] | 344064 | 197632 | 0.425595 | | 136 | bert.encoder.layer.8.attention.self.key | Linear | bias | [448] | 448 | 416 | 0.0714285 | | 137 | bert.encoder.layer.8.attention.self.value | Linear | weight | [448, 768] | 344064 | 154624 | 0.550595 | | 138 | bert.encoder.layer.8.attention.self.value | Linear | bias | [448] | 448 | 288 | 0.357143 | | 139 | bert.encoder.layer.8.attention.output.dense | Linear | weight | [768, 448] | 344064 | 148480 | 0.568452 | | 140 | bert.encoder.layer.8.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 141 | bert.encoder.layer.8.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 142 | bert.encoder.layer.8.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 143 | bert.encoder.layer.8.intermediate.dense | Linear | weight | [108, 768] | 82944 | 82944 | 0 | | 144 | bert.encoder.layer.8.intermediate.dense | Linear | bias | [108] | 108 | 108 | 0 | | 145 | bert.encoder.layer.8.output.dense | Linear | weight | [768, 108] | 82944 | 82944 | 0 | | 146 | bert.encoder.layer.8.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 147 | bert.encoder.layer.8.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 148 | bert.encoder.layer.8.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 149 | bert.encoder.layer.9.attention.self.query | Linear | weight | [320, 768] | 245760 | 144384 | 0.4125 | | 150 | bert.encoder.layer.9.attention.self.query | Linear | bias | [320] | 320 | 288 | 0.1 | | 151 | bert.encoder.layer.9.attention.self.key | Linear | weight | [320, 768] | 245760 | 155648 | 0.366667 | | 152 | bert.encoder.layer.9.attention.self.key | Linear | bias | [320] | 320 | 288 | 0.1 | | 153 | bert.encoder.layer.9.attention.self.value | Linear | weight | [320, 768] | 245760 | 63488 | 0.741667 | | 154 | bert.encoder.layer.9.attention.self.value | Linear | bias | [320] | 320 | 160 | 0.5 | | 155 | bert.encoder.layer.9.attention.output.dense | Linear | weight | [768, 320] | 245760 | 65536 | 0.733333 | | 156 | bert.encoder.layer.9.attention.output.dense | Linear | bias | [768] | 768 | 704 | 0.0833333 | | 157 | bert.encoder.layer.9.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 158 | bert.encoder.layer.9.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 159 | bert.encoder.layer.9.intermediate.dense | Linear | weight | [53, 768] | 40704 | 40704 | 5.96046e-08 | | 160 | bert.encoder.layer.9.intermediate.dense | Linear | bias | [53] | 53 | 53 | 0 | | 161 | bert.encoder.layer.9.output.dense | Linear | weight | [768, 53] | 40704 | 40704 | 5.96046e-08 | | 162 | bert.encoder.layer.9.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 163 | bert.encoder.layer.9.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 164 | bert.encoder.layer.9.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 165 | bert.encoder.layer.10.attention.self.query | Linear | weight | [384, 768] | 294912 | 158720 | 0.461806 | | 166 | bert.encoder.layer.10.attention.self.query | Linear | bias | [384] | 384 | 320 | 0.166667 | | 167 | bert.encoder.layer.10.attention.self.key | Linear | weight | [384, 768] | 294912 | 158720 | 0.461806 | | 168 | bert.encoder.layer.10.attention.self.key | Linear | bias | [384] | 384 | 320 | 0.166667 | | 169 | bert.encoder.layer.10.attention.self.value | Linear | weight | [384, 768] | 294912 | 77824 | 0.736111 | | 170 | bert.encoder.layer.10.attention.self.value | Linear | bias | [384] | 384 | 192 | 0.5 | | 171 | bert.encoder.layer.10.attention.output.dense | Linear | weight | [768, 384] | 294912 | 78848 | 0.732639 | | 172 | bert.encoder.layer.10.attention.output.dense | Linear | bias | [768] | 768 | 736 | 0.0416666 | | 173 | bert.encoder.layer.10.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 174 | bert.encoder.layer.10.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 175 | bert.encoder.layer.10.intermediate.dense | Linear | weight | [86, 768] | 66048 | 66048 | 0 | | 176 | bert.encoder.layer.10.intermediate.dense | Linear | bias | [86] | 86 | 86 | 0 | | 177 | bert.encoder.layer.10.output.dense | Linear | weight | [768, 86] | 66048 | 66048 | 0 | | 178 | bert.encoder.layer.10.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 179 | bert.encoder.layer.10.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 180 | bert.encoder.layer.10.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 181 | bert.encoder.layer.11.attention.self.query | Linear | weight | [384, 768] | 294912 | 107520 | 0.635417 | | 182 | bert.encoder.layer.11.attention.self.query | Linear | bias | [384] | 384 | 256 | 0.333333 | | 183 | bert.encoder.layer.11.attention.self.key | Linear | weight | [384, 768] | 294912 | 118784 | 0.597222 | | 184 | bert.encoder.layer.11.attention.self.key | Linear | bias | [384] | 384 | 256 | 0.333333 | | 185 | bert.encoder.layer.11.attention.self.value | Linear | weight | [384, 768] | 294912 | 62464 | 0.788194 | | 186 | bert.encoder.layer.11.attention.self.value | Linear | bias | [384] | 384 | 192 | 0.5 | | 187 | bert.encoder.layer.11.attention.output.dense | Linear | weight | [768, 384] | 294912 | 54272 | 0.815972 | | 188 | bert.encoder.layer.11.attention.output.dense | Linear | bias | [768] | 768 | 672 | 0.125 | | 189 | bert.encoder.layer.11.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 190 | bert.encoder.layer.11.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 191 | bert.encoder.layer.11.intermediate.dense | Linear | weight | [105, 768] | 80640 | 80640 | 0 | | 192 | bert.encoder.layer.11.intermediate.dense | Linear | bias | [105] | 105 | 105 | 0 | | 193 | bert.encoder.layer.11.output.dense | Linear | weight | [768, 105] | 80640 | 80640 | 0 | | 194 | bert.encoder.layer.11.output.dense | Linear | bias | [768] | 768 | 768 | 0 | | 195 | bert.encoder.layer.11.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 | | 196 | bert.encoder.layer.11.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 | | 197 | qa_outputs | Linear | weight | [2, 768] | 1536 | 1536 | 0 | | 198 | qa_outputs | Linear | bias | [2] | 2 | 2 | 0 |