bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-50.0sparse-qat-lt
/
XP_layer_wise_sparsity_global_rate_22.89.md
layer_id | layer_type | param_type | shape | nparam | nnz | sparsity | |
---|---|---|---|---|---|---|---|
0 | nncf_module.bert.embeddings.word_embeddings | NNCFEmbedding | weight | [30522, 768] | 23440896 | 23440896 | 0 |
1 | nncf_module.bert.embeddings.position_embeddings | NNCFEmbedding | weight | [512, 768] | 393216 | 393216 | 0 |
2 | nncf_module.bert.embeddings.token_type_embeddings | NNCFEmbedding | weight | [2, 768] | 1536 | 1536 | 0 |
3 | nncf_module.bert.embeddings.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
4 | nncf_module.bert.embeddings.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
5 | nncf_module.bert.encoder.layer.0.attention.self.query | NNCFLinear | weight | [320, 768] | 245760 | 106337 | 0.567314 |
6 | nncf_module.bert.encoder.layer.0.attention.self.query | NNCFLinear | bias | [320] | 320 | 320 | 0 |
7 | nncf_module.bert.encoder.layer.0.attention.self.key | NNCFLinear | weight | [320, 768] | 245760 | 112375 | 0.542745 |
8 | nncf_module.bert.encoder.layer.0.attention.self.key | NNCFLinear | bias | [320] | 320 | 320 | 0 |
9 | nncf_module.bert.encoder.layer.0.attention.self.value | NNCFLinear | weight | [320, 768] | 245760 | 131965 | 0.463033 |
10 | nncf_module.bert.encoder.layer.0.attention.self.value | NNCFLinear | bias | [320] | 320 | 320 | 0 |
11 | nncf_module.bert.encoder.layer.0.attention.output.dense | NNCFLinear | weight | [768, 320] | 245760 | 137497 | 0.440523 |
12 | nncf_module.bert.encoder.layer.0.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
13 | nncf_module.bert.encoder.layer.0.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
14 | nncf_module.bert.encoder.layer.0.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
15 | nncf_module.bert.encoder.layer.0.intermediate.dense | NNCFLinear | weight | [185, 768] | 142080 | 110056 | 0.225394 |
16 | nncf_module.bert.encoder.layer.0.intermediate.dense | NNCFLinear | bias | [185] | 185 | 185 | 0 |
17 | nncf_module.bert.encoder.layer.0.output.dense | NNCFLinear | weight | [768, 185] | 142080 | 108631 | 0.235424 |
18 | nncf_module.bert.encoder.layer.0.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
19 | nncf_module.bert.encoder.layer.0.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
20 | nncf_module.bert.encoder.layer.0.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
21 | nncf_module.bert.encoder.layer.1.attention.self.query | NNCFLinear | weight | [320, 768] | 245760 | 136222 | 0.445711 |
22 | nncf_module.bert.encoder.layer.1.attention.self.query | NNCFLinear | bias | [320] | 320 | 320 | 0 |
23 | nncf_module.bert.encoder.layer.1.attention.self.key | NNCFLinear | weight | [320, 768] | 245760 | 136267 | 0.445528 |
24 | nncf_module.bert.encoder.layer.1.attention.self.key | NNCFLinear | bias | [320] | 320 | 320 | 0 |
25 | nncf_module.bert.encoder.layer.1.attention.self.value | NNCFLinear | weight | [320, 768] | 245760 | 124892 | 0.491813 |
26 | nncf_module.bert.encoder.layer.1.attention.self.value | NNCFLinear | bias | [320] | 320 | 320 | 0 |
27 | nncf_module.bert.encoder.layer.1.attention.output.dense | NNCFLinear | weight | [768, 320] | 245760 | 130185 | 0.470276 |
28 | nncf_module.bert.encoder.layer.1.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
29 | nncf_module.bert.encoder.layer.1.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
30 | nncf_module.bert.encoder.layer.1.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
31 | nncf_module.bert.encoder.layer.1.intermediate.dense | NNCFLinear | weight | [315, 768] | 241920 | 176203 | 0.271648 |
32 | nncf_module.bert.encoder.layer.1.intermediate.dense | NNCFLinear | bias | [315] | 315 | 315 | 0 |
33 | nncf_module.bert.encoder.layer.1.output.dense | NNCFLinear | weight | [768, 315] | 241920 | 172407 | 0.287339 |
34 | nncf_module.bert.encoder.layer.1.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
35 | nncf_module.bert.encoder.layer.1.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
36 | nncf_module.bert.encoder.layer.1.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
37 | nncf_module.bert.encoder.layer.2.attention.self.query | NNCFLinear | weight | [576, 768] | 442368 | 198811 | 0.550575 |
38 | nncf_module.bert.encoder.layer.2.attention.self.query | NNCFLinear | bias | [576] | 576 | 576 | 0 |
39 | nncf_module.bert.encoder.layer.2.attention.self.key | NNCFLinear | weight | [576, 768] | 442368 | 201526 | 0.544438 |
40 | nncf_module.bert.encoder.layer.2.attention.self.key | NNCFLinear | bias | [576] | 576 | 576 | 0 |
41 | nncf_module.bert.encoder.layer.2.attention.self.value | NNCFLinear | weight | [576, 768] | 442368 | 163541 | 0.630306 |
42 | nncf_module.bert.encoder.layer.2.attention.self.value | NNCFLinear | bias | [576] | 576 | 576 | 0 |
43 | nncf_module.bert.encoder.layer.2.attention.output.dense | NNCFLinear | weight | [768, 576] | 442368 | 167245 | 0.621932 |
44 | nncf_module.bert.encoder.layer.2.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
45 | nncf_module.bert.encoder.layer.2.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
46 | nncf_module.bert.encoder.layer.2.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
47 | nncf_module.bert.encoder.layer.2.intermediate.dense | NNCFLinear | weight | [339, 768] | 260352 | 185491 | 0.287538 |
48 | nncf_module.bert.encoder.layer.2.intermediate.dense | NNCFLinear | bias | [339] | 339 | 339 | 0 |
49 | nncf_module.bert.encoder.layer.2.output.dense | NNCFLinear | weight | [768, 339] | 260352 | 183083 | 0.296787 |
50 | nncf_module.bert.encoder.layer.2.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
51 | nncf_module.bert.encoder.layer.2.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
52 | nncf_module.bert.encoder.layer.2.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
53 | nncf_module.bert.encoder.layer.3.attention.self.query | NNCFLinear | weight | [576, 768] | 442368 | 205898 | 0.534555 |
54 | nncf_module.bert.encoder.layer.3.attention.self.query | NNCFLinear | bias | [576] | 576 | 576 | 0 |
55 | nncf_module.bert.encoder.layer.3.attention.self.key | NNCFLinear | weight | [576, 768] | 442368 | 217621 | 0.508054 |
56 | nncf_module.bert.encoder.layer.3.attention.self.key | NNCFLinear | bias | [576] | 576 | 576 | 0 |
57 | nncf_module.bert.encoder.layer.3.attention.self.value | NNCFLinear | weight | [576, 768] | 442368 | 209726 | 0.525901 |
58 | nncf_module.bert.encoder.layer.3.attention.self.value | NNCFLinear | bias | [576] | 576 | 576 | 0 |
59 | nncf_module.bert.encoder.layer.3.attention.output.dense | NNCFLinear | weight | [768, 576] | 442368 | 208038 | 0.529717 |
60 | nncf_module.bert.encoder.layer.3.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
61 | nncf_module.bert.encoder.layer.3.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
62 | nncf_module.bert.encoder.layer.3.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
63 | nncf_module.bert.encoder.layer.3.intermediate.dense | NNCFLinear | weight | [368, 768] | 282624 | 198154 | 0.298878 |
64 | nncf_module.bert.encoder.layer.3.intermediate.dense | NNCFLinear | bias | [368] | 368 | 368 | 0 |
65 | nncf_module.bert.encoder.layer.3.output.dense | NNCFLinear | weight | [768, 368] | 282624 | 194127 | 0.313126 |
66 | nncf_module.bert.encoder.layer.3.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
67 | nncf_module.bert.encoder.layer.3.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
68 | nncf_module.bert.encoder.layer.3.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
69 | nncf_module.bert.encoder.layer.4.attention.self.query | NNCFLinear | weight | [576, 768] | 442368 | 212567 | 0.519479 |
70 | nncf_module.bert.encoder.layer.4.attention.self.query | NNCFLinear | bias | [576] | 576 | 576 | 0 |
71 | nncf_module.bert.encoder.layer.4.attention.self.key | NNCFLinear | weight | [576, 768] | 442368 | 214788 | 0.514459 |
72 | nncf_module.bert.encoder.layer.4.attention.self.key | NNCFLinear | bias | [576] | 576 | 576 | 0 |
73 | nncf_module.bert.encoder.layer.4.attention.self.value | NNCFLinear | weight | [576, 768] | 442368 | 197159 | 0.55431 |
74 | nncf_module.bert.encoder.layer.4.attention.self.value | NNCFLinear | bias | [576] | 576 | 576 | 0 |
75 | nncf_module.bert.encoder.layer.4.attention.output.dense | NNCFLinear | weight | [768, 576] | 442368 | 192495 | 0.564853 |
76 | nncf_module.bert.encoder.layer.4.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
77 | nncf_module.bert.encoder.layer.4.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
78 | nncf_module.bert.encoder.layer.4.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
79 | nncf_module.bert.encoder.layer.4.intermediate.dense | NNCFLinear | weight | [386, 768] | 296448 | 205830 | 0.305679 |
80 | nncf_module.bert.encoder.layer.4.intermediate.dense | NNCFLinear | bias | [386] | 386 | 386 | 0 |
81 | nncf_module.bert.encoder.layer.4.output.dense | NNCFLinear | weight | [768, 386] | 296448 | 199567 | 0.326806 |
82 | nncf_module.bert.encoder.layer.4.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
83 | nncf_module.bert.encoder.layer.4.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
84 | nncf_module.bert.encoder.layer.4.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
85 | nncf_module.bert.encoder.layer.5.attention.self.query | NNCFLinear | weight | [384, 768] | 294912 | 131257 | 0.554928 |
86 | nncf_module.bert.encoder.layer.5.attention.self.query | NNCFLinear | bias | [384] | 384 | 384 | 0 |
87 | nncf_module.bert.encoder.layer.5.attention.self.key | NNCFLinear | weight | [384, 768] | 294912 | 154458 | 0.476257 |
88 | nncf_module.bert.encoder.layer.5.attention.self.key | NNCFLinear | bias | [384] | 384 | 384 | 0 |
89 | nncf_module.bert.encoder.layer.5.attention.self.value | NNCFLinear | weight | [384, 768] | 294912 | 159646 | 0.458666 |
90 | nncf_module.bert.encoder.layer.5.attention.self.value | NNCFLinear | bias | [384] | 384 | 384 | 0 |
91 | nncf_module.bert.encoder.layer.5.attention.output.dense | NNCFLinear | weight | [768, 384] | 294912 | 156889 | 0.468014 |
92 | nncf_module.bert.encoder.layer.5.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
93 | nncf_module.bert.encoder.layer.5.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
94 | nncf_module.bert.encoder.layer.5.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
95 | nncf_module.bert.encoder.layer.5.intermediate.dense | NNCFLinear | weight | [336, 768] | 258048 | 184774 | 0.283955 |
96 | nncf_module.bert.encoder.layer.5.intermediate.dense | NNCFLinear | bias | [336] | 336 | 336 | 0 |
97 | nncf_module.bert.encoder.layer.5.output.dense | NNCFLinear | weight | [768, 336] | 258048 | 178574 | 0.307981 |
98 | nncf_module.bert.encoder.layer.5.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
99 | nncf_module.bert.encoder.layer.5.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
100 | nncf_module.bert.encoder.layer.5.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
101 | nncf_module.bert.encoder.layer.6.attention.self.query | NNCFLinear | weight | [448, 768] | 344064 | 153126 | 0.554949 |
102 | nncf_module.bert.encoder.layer.6.attention.self.query | NNCFLinear | bias | [448] | 448 | 448 | 0 |
103 | nncf_module.bert.encoder.layer.6.attention.self.key | NNCFLinear | weight | [448, 768] | 344064 | 169706 | 0.50676 |
104 | nncf_module.bert.encoder.layer.6.attention.self.key | NNCFLinear | bias | [448] | 448 | 448 | 0 |
105 | nncf_module.bert.encoder.layer.6.attention.self.value | NNCFLinear | weight | [448, 768] | 344064 | 154213 | 0.55179 |
106 | nncf_module.bert.encoder.layer.6.attention.self.value | NNCFLinear | bias | [448] | 448 | 448 | 0 |
107 | nncf_module.bert.encoder.layer.6.attention.output.dense | NNCFLinear | weight | [768, 448] | 344064 | 148815 | 0.567479 |
108 | nncf_module.bert.encoder.layer.6.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
109 | nncf_module.bert.encoder.layer.6.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
110 | nncf_module.bert.encoder.layer.6.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
111 | nncf_module.bert.encoder.layer.6.intermediate.dense | NNCFLinear | weight | [280, 768] | 215040 | 158800 | 0.261533 |
112 | nncf_module.bert.encoder.layer.6.intermediate.dense | NNCFLinear | bias | [280] | 280 | 280 | 0 |
113 | nncf_module.bert.encoder.layer.6.output.dense | NNCFLinear | weight | [768, 280] | 215040 | 156397 | 0.272707 |
114 | nncf_module.bert.encoder.layer.6.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
115 | nncf_module.bert.encoder.layer.6.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
116 | nncf_module.bert.encoder.layer.6.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
117 | nncf_module.bert.encoder.layer.7.attention.self.query | NNCFLinear | weight | [448, 768] | 344064 | 153876 | 0.552769 |
118 | nncf_module.bert.encoder.layer.7.attention.self.query | NNCFLinear | bias | [448] | 448 | 448 | 0 |
119 | nncf_module.bert.encoder.layer.7.attention.self.key | NNCFLinear | weight | [448, 768] | 344064 | 180384 | 0.475725 |
120 | nncf_module.bert.encoder.layer.7.attention.self.key | NNCFLinear | bias | [448] | 448 | 448 | 0 |
121 | nncf_module.bert.encoder.layer.7.attention.self.value | NNCFLinear | weight | [448, 768] | 344064 | 166552 | 0.515927 |
122 | nncf_module.bert.encoder.layer.7.attention.self.value | NNCFLinear | bias | [448] | 448 | 448 | 0 |
123 | nncf_module.bert.encoder.layer.7.attention.output.dense | NNCFLinear | weight | [768, 448] | 344064 | 160346 | 0.533965 |
124 | nncf_module.bert.encoder.layer.7.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
125 | nncf_module.bert.encoder.layer.7.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
126 | nncf_module.bert.encoder.layer.7.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
127 | nncf_module.bert.encoder.layer.7.intermediate.dense | NNCFLinear | weight | [211, 768] | 162048 | 125197 | 0.227408 |
128 | nncf_module.bert.encoder.layer.7.intermediate.dense | NNCFLinear | bias | [211] | 211 | 211 | 0 |
129 | nncf_module.bert.encoder.layer.7.output.dense | NNCFLinear | weight | [768, 211] | 162048 | 123451 | 0.238182 |
130 | nncf_module.bert.encoder.layer.7.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
131 | nncf_module.bert.encoder.layer.7.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
132 | nncf_module.bert.encoder.layer.7.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
133 | nncf_module.bert.encoder.layer.8.attention.self.query | NNCFLinear | weight | [448, 768] | 344064 | 149419 | 0.565723 |
134 | nncf_module.bert.encoder.layer.8.attention.self.query | NNCFLinear | bias | [448] | 448 | 448 | 0 |
135 | nncf_module.bert.encoder.layer.8.attention.self.key | NNCFLinear | weight | [448, 768] | 344064 | 150699 | 0.562003 |
136 | nncf_module.bert.encoder.layer.8.attention.self.key | NNCFLinear | bias | [448] | 448 | 448 | 0 |
137 | nncf_module.bert.encoder.layer.8.attention.self.value | NNCFLinear | weight | [448, 768] | 344064 | 124770 | 0.637364 |
138 | nncf_module.bert.encoder.layer.8.attention.self.value | NNCFLinear | bias | [448] | 448 | 448 | 0 |
139 | nncf_module.bert.encoder.layer.8.attention.output.dense | NNCFLinear | weight | [768, 448] | 344064 | 120648 | 0.649344 |
140 | nncf_module.bert.encoder.layer.8.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
141 | nncf_module.bert.encoder.layer.8.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
142 | nncf_module.bert.encoder.layer.8.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
143 | nncf_module.bert.encoder.layer.8.intermediate.dense | NNCFLinear | weight | [108, 768] | 82944 | 68989 | 0.168246 |
144 | nncf_module.bert.encoder.layer.8.intermediate.dense | NNCFLinear | bias | [108] | 108 | 108 | 0 |
145 | nncf_module.bert.encoder.layer.8.output.dense | NNCFLinear | weight | [768, 108] | 82944 | 68556 | 0.173466 |
146 | nncf_module.bert.encoder.layer.8.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
147 | nncf_module.bert.encoder.layer.8.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
148 | nncf_module.bert.encoder.layer.8.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
149 | nncf_module.bert.encoder.layer.9.attention.self.query | NNCFLinear | weight | [320, 768] | 245760 | 121225 | 0.506734 |
150 | nncf_module.bert.encoder.layer.9.attention.self.query | NNCFLinear | bias | [320] | 320 | 320 | 0 |
151 | nncf_module.bert.encoder.layer.9.attention.self.key | NNCFLinear | weight | [320, 768] | 245760 | 114789 | 0.532922 |
152 | nncf_module.bert.encoder.layer.9.attention.self.key | NNCFLinear | bias | [320] | 320 | 320 | 0 |
153 | nncf_module.bert.encoder.layer.9.attention.self.value | NNCFLinear | weight | [320, 768] | 245760 | 69260 | 0.71818 |
154 | nncf_module.bert.encoder.layer.9.attention.self.value | NNCFLinear | bias | [320] | 320 | 320 | 0 |
155 | nncf_module.bert.encoder.layer.9.attention.output.dense | NNCFLinear | weight | [768, 320] | 245760 | 73575 | 0.700623 |
156 | nncf_module.bert.encoder.layer.9.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
157 | nncf_module.bert.encoder.layer.9.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
158 | nncf_module.bert.encoder.layer.9.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
159 | nncf_module.bert.encoder.layer.9.intermediate.dense | NNCFLinear | weight | [53, 768] | 40704 | 35399 | 0.130331 |
160 | nncf_module.bert.encoder.layer.9.intermediate.dense | NNCFLinear | bias | [53] | 53 | 53 | 0 |
161 | nncf_module.bert.encoder.layer.9.output.dense | NNCFLinear | weight | [768, 53] | 40704 | 34918 | 0.142148 |
162 | nncf_module.bert.encoder.layer.9.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
163 | nncf_module.bert.encoder.layer.9.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
164 | nncf_module.bert.encoder.layer.9.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
165 | nncf_module.bert.encoder.layer.10.attention.self.query | NNCFLinear | weight | [384, 768] | 294912 | 128113 | 0.565589 |
166 | nncf_module.bert.encoder.layer.10.attention.self.query | NNCFLinear | bias | [384] | 384 | 384 | 0 |
167 | nncf_module.bert.encoder.layer.10.attention.self.key | NNCFLinear | weight | [384, 768] | 294912 | 124553 | 0.57766 |
168 | nncf_module.bert.encoder.layer.10.attention.self.key | NNCFLinear | bias | [384] | 384 | 384 | 0 |
169 | nncf_module.bert.encoder.layer.10.attention.self.value | NNCFLinear | weight | [384, 768] | 294912 | 79608 | 0.730062 |
170 | nncf_module.bert.encoder.layer.10.attention.self.value | NNCFLinear | bias | [384] | 384 | 384 | 0 |
171 | nncf_module.bert.encoder.layer.10.attention.output.dense | NNCFLinear | weight | [768, 384] | 294912 | 85158 | 0.711243 |
172 | nncf_module.bert.encoder.layer.10.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
173 | nncf_module.bert.encoder.layer.10.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
174 | nncf_module.bert.encoder.layer.10.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
175 | nncf_module.bert.encoder.layer.10.intermediate.dense | NNCFLinear | weight | [86, 768] | 66048 | 55025 | 0.166894 |
176 | nncf_module.bert.encoder.layer.10.intermediate.dense | NNCFLinear | bias | [86] | 86 | 86 | 0 |
177 | nncf_module.bert.encoder.layer.10.output.dense | NNCFLinear | weight | [768, 86] | 66048 | 54584 | 0.173571 |
178 | nncf_module.bert.encoder.layer.10.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
179 | nncf_module.bert.encoder.layer.10.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
180 | nncf_module.bert.encoder.layer.10.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
181 | nncf_module.bert.encoder.layer.11.attention.self.query | NNCFLinear | weight | [384, 768] | 294912 | 104737 | 0.644853 |
182 | nncf_module.bert.encoder.layer.11.attention.self.query | NNCFLinear | bias | [384] | 384 | 384 | 0 |
183 | nncf_module.bert.encoder.layer.11.attention.self.key | NNCFLinear | weight | [384, 768] | 294912 | 102558 | 0.652242 |
184 | nncf_module.bert.encoder.layer.11.attention.self.key | NNCFLinear | bias | [384] | 384 | 384 | 0 |
185 | nncf_module.bert.encoder.layer.11.attention.self.value | NNCFLinear | weight | [384, 768] | 294912 | 64855 | 0.780087 |
186 | nncf_module.bert.encoder.layer.11.attention.self.value | NNCFLinear | bias | [384] | 384 | 384 | 0 |
187 | nncf_module.bert.encoder.layer.11.attention.output.dense | NNCFLinear | weight | [768, 384] | 294912 | 69674 | 0.763747 |
188 | nncf_module.bert.encoder.layer.11.attention.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
189 | nncf_module.bert.encoder.layer.11.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
190 | nncf_module.bert.encoder.layer.11.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
191 | nncf_module.bert.encoder.layer.11.intermediate.dense | NNCFLinear | weight | [105, 768] | 80640 | 67724 | 0.160169 |
192 | nncf_module.bert.encoder.layer.11.intermediate.dense | NNCFLinear | bias | [105] | 105 | 105 | 0 |
193 | nncf_module.bert.encoder.layer.11.output.dense | NNCFLinear | weight | [768, 105] | 80640 | 67519 | 0.162711 |
194 | nncf_module.bert.encoder.layer.11.output.dense | NNCFLinear | bias | [768] | 768 | 768 | 0 |
195 | nncf_module.bert.encoder.layer.11.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
196 | nncf_module.bert.encoder.layer.11.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
197 | nncf_module.qa_outputs | NNCFLinear | weight | [2, 768] | 1536 | 1536 | 0 |
198 | nncf_module.qa_outputs | NNCFLinear | bias | [2] | 2 | 2 | 0 |