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 / linear_layer_sparsity_85M_params_90.00_sparsity.md
Chua, Vui Seng
Add collaterals
0e66ada
preview code
|
raw
history blame
10.7 kB
| | layer_id | layer_type | param_type | shape | nparam | nnz | sparsity |
|----:|:---------------------------------------------------------|:-------------|:-------------|:------------|---------:|-------:|-----------:|
| 5 | nncf_module.bert.encoder.layer.0.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 7 | nncf_module.bert.encoder.layer.0.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 9 | nncf_module.bert.encoder.layer.0.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 11 | nncf_module.bert.encoder.layer.0.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 15 | nncf_module.bert.encoder.layer.0.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 17 | nncf_module.bert.encoder.layer.0.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 21 | nncf_module.bert.encoder.layer.1.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 23 | nncf_module.bert.encoder.layer.1.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 25 | nncf_module.bert.encoder.layer.1.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 27 | nncf_module.bert.encoder.layer.1.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 31 | nncf_module.bert.encoder.layer.1.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 33 | nncf_module.bert.encoder.layer.1.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 37 | nncf_module.bert.encoder.layer.2.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 39 | nncf_module.bert.encoder.layer.2.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 41 | nncf_module.bert.encoder.layer.2.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 43 | nncf_module.bert.encoder.layer.2.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 47 | nncf_module.bert.encoder.layer.2.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 49 | nncf_module.bert.encoder.layer.2.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 53 | nncf_module.bert.encoder.layer.3.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 55 | nncf_module.bert.encoder.layer.3.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 57 | nncf_module.bert.encoder.layer.3.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 59 | nncf_module.bert.encoder.layer.3.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 63 | nncf_module.bert.encoder.layer.3.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 65 | nncf_module.bert.encoder.layer.3.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 69 | nncf_module.bert.encoder.layer.4.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 71 | nncf_module.bert.encoder.layer.4.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 73 | nncf_module.bert.encoder.layer.4.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 75 | nncf_module.bert.encoder.layer.4.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 79 | nncf_module.bert.encoder.layer.4.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 81 | nncf_module.bert.encoder.layer.4.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 85 | nncf_module.bert.encoder.layer.5.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 87 | nncf_module.bert.encoder.layer.5.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 89 | nncf_module.bert.encoder.layer.5.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 91 | nncf_module.bert.encoder.layer.5.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 95 | nncf_module.bert.encoder.layer.5.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 97 | nncf_module.bert.encoder.layer.5.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 101 | nncf_module.bert.encoder.layer.6.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 103 | nncf_module.bert.encoder.layer.6.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 105 | nncf_module.bert.encoder.layer.6.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 107 | nncf_module.bert.encoder.layer.6.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 111 | nncf_module.bert.encoder.layer.6.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 113 | nncf_module.bert.encoder.layer.6.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 117 | nncf_module.bert.encoder.layer.7.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 119 | nncf_module.bert.encoder.layer.7.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 121 | nncf_module.bert.encoder.layer.7.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 123 | nncf_module.bert.encoder.layer.7.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 127 | nncf_module.bert.encoder.layer.7.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 129 | nncf_module.bert.encoder.layer.7.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235929 | 0.9 |
| 133 | nncf_module.bert.encoder.layer.8.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 135 | nncf_module.bert.encoder.layer.8.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 137 | nncf_module.bert.encoder.layer.8.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 139 | nncf_module.bert.encoder.layer.8.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 143 | nncf_module.bert.encoder.layer.8.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 145 | nncf_module.bert.encoder.layer.8.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 149 | nncf_module.bert.encoder.layer.9.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 151 | nncf_module.bert.encoder.layer.9.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 153 | nncf_module.bert.encoder.layer.9.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 155 | nncf_module.bert.encoder.layer.9.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 159 | nncf_module.bert.encoder.layer.9.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 161 | nncf_module.bert.encoder.layer.9.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |
| 165 | nncf_module.bert.encoder.layer.10.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 167 | nncf_module.bert.encoder.layer.10.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 169 | nncf_module.bert.encoder.layer.10.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 171 | nncf_module.bert.encoder.layer.10.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 175 | nncf_module.bert.encoder.layer.10.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 177 | nncf_module.bert.encoder.layer.10.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235929 | 0.9 |
| 181 | nncf_module.bert.encoder.layer.11.attention.self.query | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 183 | nncf_module.bert.encoder.layer.11.attention.self.key | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 185 | nncf_module.bert.encoder.layer.11.attention.self.value | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 187 | nncf_module.bert.encoder.layer.11.attention.output.dense | NNCFLinear | weight | [768, 768] | 589824 | 58983 | 0.899999 |
| 191 | nncf_module.bert.encoder.layer.11.intermediate.dense | NNCFLinear | weight | [3072, 768] | 2359296 | 235930 | 0.9 |
| 193 | nncf_module.bert.encoder.layer.11.output.dense | NNCFLinear | weight | [768, 3072] | 2359296 | 235930 | 0.9 |