bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-lt
/
XP_layer_wise_sparsity_global_rate_26.51.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 | 93583 | 0.61921 |
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 | 98270 | 0.600138 |
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 | 113605 | 0.53774 |
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 | 117208 | 0.523079 |
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 | 97073 | 0.316772 |
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 | 94692 | 0.33353 |
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 | 118436 | 0.518083 |
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 | 118116 | 0.519385 |
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 | 107511 | 0.562537 |
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 | 111189 | 0.547571 |
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 | 148783 | 0.384991 |
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 | 143166 | 0.408209 |
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 | 162735 | 0.632128 |
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 | 164795 | 0.627471 |
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 | 135670 | 0.69331 |
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 | 138445 | 0.687037 |
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 | 154035 | 0.408359 |
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 | 150816 | 0.420723 |
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 | 170623 | 0.614296 |
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 | 178401 | 0.596714 |
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 | 171905 | 0.611398 |
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 | 169172 | 0.617576 |
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 | 163163 | 0.422685 |
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 | 157506 | 0.442701 |
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 | 175772 | 0.602657 |
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 | 177087 | 0.599684 |
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 | 163996 | 0.629277 |
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 | 159335 | 0.639813 |
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 | 167726 | 0.434214 |
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 | 159865 | 0.460732 |
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 | 114186 | 0.612813 |
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 | 132782 | 0.549757 |
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 | 134830 | 0.542813 |
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 | 131941 | 0.552609 |
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 | 153916 | 0.403537 |
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 | 145794 | 0.435012 |
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 | 131878 | 0.616705 |
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 | 144502 | 0.580014 |
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 | 130911 | 0.619516 |
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 | 125928 | 0.633998 |
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 | 135283 | 0.370894 |
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 | 131619 | 0.387932 |
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 | 132120 | 0.616002 |
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 | 152223 | 0.557574 |
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 | 141066 | 0.590001 |
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 | 135662 | 0.605707 |
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 | 109590 | 0.323719 |
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 | 107335 | 0.337635 |
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 | 129148 | 0.62464 |
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 | 130060 | 0.621989 |
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 | 108162 | 0.685634 |
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 | 103447 | 0.699338 |
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 | 63275 | 0.237136 |
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 | 62725 | 0.243767 |
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 | 107145 | 0.564026 |
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 | 101811 | 0.58573 |
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 | 52182 | 0.787671 |
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 | 53210 | 0.783488 |
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 | 33461 | 0.177943 |
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 | 32551 | 0.2003 |
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 | 112430 | 0.618768 |
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 | 109594 | 0.628384 |
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 | 61774 | 0.790534 |
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 | 64183 | 0.782366 |
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 | 50455 | 0.236086 |
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 | 49741 | 0.246896 |
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 | 88129 | 0.701168 |
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 | 85288 | 0.710802 |
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 | 47258 | 0.839756 |
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 | 49311 | 0.832794 |
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 | 62254 | 0.228001 |
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 | 61669 | 0.235255 |
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 |