Hugging Face's logo

vuiseng9
/
bert-base-squadv1-pruneofa-90pc-bt-qat-lt

Transformers
PyTorch
ONNX
bert
Inference Endpoints
Model card Files Community
bert-base-squadv1-pruneofa-90pc-bt-qat-lt / layer_wise_sparsity_global_rate_70.20.md
Chua, Vui Seng
Add collaterals
0e66ada
preview code
|
raw history blame contribute delete
No virus
30.6 kB
| | 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 6 | nncf_module.bert.encoder.layer.0.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 7 | nncf_module.bert.encoder.layer.0.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 8 | nncf_module.bert.encoder.layer.0.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 9 | nncf_module.bert.encoder.layer.0.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 10 | nncf_module.bert.encoder.layer.0.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 11 | nncf_module.bert.encoder.layer.0.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 16 | nncf_module.bert.encoder.layer.0.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 17 | nncf_module.bert.encoder.layer.0.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 22 | nncf_module.bert.encoder.layer.1.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 23 | nncf_module.bert.encoder.layer.1.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 24 | nncf_module.bert.encoder.layer.1.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 25 | nncf_module.bert.encoder.layer.1.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 26 | nncf_module.bert.encoder.layer.1.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 27 | nncf_module.bert.encoder.layer.1.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 32 | nncf_module.bert.encoder.layer.1.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 33 | nncf_module.bert.encoder.layer.1.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 38 | nncf_module.bert.encoder.layer.2.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 39 | nncf_module.bert.encoder.layer.2.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 40 | nncf_module.bert.encoder.layer.2.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 41 | nncf_module.bert.encoder.layer.2.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 42 | nncf_module.bert.encoder.layer.2.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 43 | nncf_module.bert.encoder.layer.2.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 48 | nncf_module.bert.encoder.layer.2.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 49 | nncf_module.bert.encoder.layer.2.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 54 | nncf_module.bert.encoder.layer.3.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 55 | nncf_module.bert.encoder.layer.3.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 56 | nncf_module.bert.encoder.layer.3.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 57 | nncf_module.bert.encoder.layer.3.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 58 | nncf_module.bert.encoder.layer.3.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 59 | nncf_module.bert.encoder.layer.3.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 64 | nncf_module.bert.encoder.layer.3.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 65 | nncf_module.bert.encoder.layer.3.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 70 | nncf_module.bert.encoder.layer.4.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 71 | nncf_module.bert.encoder.layer.4.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 72 | nncf_module.bert.encoder.layer.4.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 73 | nncf_module.bert.encoder.layer.4.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 74 | nncf_module.bert.encoder.layer.4.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 75 | nncf_module.bert.encoder.layer.4.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 80 | nncf_module.bert.encoder.layer.4.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 81 | nncf_module.bert.encoder.layer.4.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 86 | nncf_module.bert.encoder.layer.5.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 87 | nncf_module.bert.encoder.layer.5.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 88 | nncf_module.bert.encoder.layer.5.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 89 | nncf_module.bert.encoder.layer.5.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 90 | nncf_module.bert.encoder.layer.5.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 91 | nncf_module.bert.encoder.layer.5.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 96 | nncf_module.bert.encoder.layer.5.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 97 | nncf_module.bert.encoder.layer.5.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 102 | nncf_module.bert.encoder.layer.6.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 103 | nncf_module.bert.encoder.layer.6.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 104 | nncf_module.bert.encoder.layer.6.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 105 | nncf_module.bert.encoder.layer.6.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 106 | nncf_module.bert.encoder.layer.6.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 107 | nncf_module.bert.encoder.layer.6.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 112 | nncf_module.bert.encoder.layer.6.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 113 | nncf_module.bert.encoder.layer.6.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 118 | nncf_module.bert.encoder.layer.7.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 119 | nncf_module.bert.encoder.layer.7.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 120 | nncf_module.bert.encoder.layer.7.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 121 | nncf_module.bert.encoder.layer.7.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 122 | nncf_module.bert.encoder.layer.7.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 123 | nncf_module.bert.encoder.layer.7.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 128 | nncf_module.bert.encoder.layer.7.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 129 | nncf_module.bert.encoder.layer.7.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235929 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 134 | nncf_module.bert.encoder.layer.8.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 135 | nncf_module.bert.encoder.layer.8.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 136 | nncf_module.bert.encoder.layer.8.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 137 | nncf_module.bert.encoder.layer.8.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 138 | nncf_module.bert.encoder.layer.8.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 139 | nncf_module.bert.encoder.layer.8.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 144 | nncf_module.bert.encoder.layer.8.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 145 | nncf_module.bert.encoder.layer.8.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 150 | nncf_module.bert.encoder.layer.9.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 151 | nncf_module.bert.encoder.layer.9.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 152 | nncf_module.bert.encoder.layer.9.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 153 | nncf_module.bert.encoder.layer.9.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 154 | nncf_module.bert.encoder.layer.9.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 155 | nncf_module.bert.encoder.layer.9.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 160 | nncf_module.bert.encoder.layer.9.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 161 | nncf_module.bert.encoder.layer.9.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 166 | nncf_module.bert.encoder.layer.10.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 167 | nncf_module.bert.encoder.layer.10.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 168 | nncf_module.bert.encoder.layer.10.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 169 | nncf_module.bert.encoder.layer.10.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 170 | nncf_module.bert.encoder.layer.10.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 171 | nncf_module.bert.encoder.layer.10.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 176 | nncf_module.bert.encoder.layer.10.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 177 | nncf_module.bert.encoder.layer.10.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235929 | 0.9 |
| 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 | [768, 768] | 589824 | 58983 | 0.899999 |
| 182 | nncf_module.bert.encoder.layer.11.attention.self.query | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 183 | nncf_module.bert.encoder.layer.11.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 184 | nncf_module.bert.encoder.layer.11.attention.self.key | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 185 | nncf_module.bert.encoder.layer.11.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 186 | nncf_module.bert.encoder.layer.11.attention.self.value | NNCFLinear | bias | [768] | 768 | 768 | 0 |
| 187 | nncf_module.bert.encoder.layer.11.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 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 | [3072, 768] | 2359296 | 235930 | 0.9 |
| 192 | nncf_module.bert.encoder.layer.11.intermediate.dense | NNCFLinear | bias | [3072] | 3072 | 3072 | 0 |
| 193 | nncf_module.bert.encoder.layer.11.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 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 |