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.csv
Chua, Vui Seng
Add collaterals
0e66ada
raw history blame contribute delete
No virus
8.69 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]",589824,58983,0.8999989628791809
7,nncf_module.bert.encoder.layer.0.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
9,nncf_module.bert.encoder.layer.0.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
11,nncf_module.bert.encoder.layer.0.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
15,nncf_module.bert.encoder.layer.0.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
17,nncf_module.bert.encoder.layer.0.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
21,nncf_module.bert.encoder.layer.1.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
23,nncf_module.bert.encoder.layer.1.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
25,nncf_module.bert.encoder.layer.1.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
27,nncf_module.bert.encoder.layer.1.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
31,nncf_module.bert.encoder.layer.1.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
33,nncf_module.bert.encoder.layer.1.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
37,nncf_module.bert.encoder.layer.2.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
39,nncf_module.bert.encoder.layer.2.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
41,nncf_module.bert.encoder.layer.2.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
43,nncf_module.bert.encoder.layer.2.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
47,nncf_module.bert.encoder.layer.2.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
49,nncf_module.bert.encoder.layer.2.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
53,nncf_module.bert.encoder.layer.3.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
55,nncf_module.bert.encoder.layer.3.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
57,nncf_module.bert.encoder.layer.3.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
59,nncf_module.bert.encoder.layer.3.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
63,nncf_module.bert.encoder.layer.3.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
65,nncf_module.bert.encoder.layer.3.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
69,nncf_module.bert.encoder.layer.4.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
71,nncf_module.bert.encoder.layer.4.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
73,nncf_module.bert.encoder.layer.4.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
75,nncf_module.bert.encoder.layer.4.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
79,nncf_module.bert.encoder.layer.4.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
81,nncf_module.bert.encoder.layer.4.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
85,nncf_module.bert.encoder.layer.5.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
87,nncf_module.bert.encoder.layer.5.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
89,nncf_module.bert.encoder.layer.5.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
91,nncf_module.bert.encoder.layer.5.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
95,nncf_module.bert.encoder.layer.5.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
97,nncf_module.bert.encoder.layer.5.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
101,nncf_module.bert.encoder.layer.6.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
103,nncf_module.bert.encoder.layer.6.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
105,nncf_module.bert.encoder.layer.6.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
107,nncf_module.bert.encoder.layer.6.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
111,nncf_module.bert.encoder.layer.6.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
113,nncf_module.bert.encoder.layer.6.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
117,nncf_module.bert.encoder.layer.7.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
119,nncf_module.bert.encoder.layer.7.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
121,nncf_module.bert.encoder.layer.7.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
123,nncf_module.bert.encoder.layer.7.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
127,nncf_module.bert.encoder.layer.7.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
129,nncf_module.bert.encoder.layer.7.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235929,0.900000274181366
133,nncf_module.bert.encoder.layer.8.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
135,nncf_module.bert.encoder.layer.8.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
137,nncf_module.bert.encoder.layer.8.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
139,nncf_module.bert.encoder.layer.8.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
143,nncf_module.bert.encoder.layer.8.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
145,nncf_module.bert.encoder.layer.8.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
149,nncf_module.bert.encoder.layer.9.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
151,nncf_module.bert.encoder.layer.9.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
153,nncf_module.bert.encoder.layer.9.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
155,nncf_module.bert.encoder.layer.9.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
159,nncf_module.bert.encoder.layer.9.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
161,nncf_module.bert.encoder.layer.9.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525
165,nncf_module.bert.encoder.layer.10.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
167,nncf_module.bert.encoder.layer.10.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
169,nncf_module.bert.encoder.layer.10.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
171,nncf_module.bert.encoder.layer.10.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
175,nncf_module.bert.encoder.layer.10.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
177,nncf_module.bert.encoder.layer.10.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235929,0.900000274181366
181,nncf_module.bert.encoder.layer.11.attention.self.query,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
183,nncf_module.bert.encoder.layer.11.attention.self.key,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
185,nncf_module.bert.encoder.layer.11.attention.self.value,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
187,nncf_module.bert.encoder.layer.11.attention.output.dense,NNCFLinear,weight,"[768, 768]",589824,58983,0.8999989628791809
191,nncf_module.bert.encoder.layer.11.intermediate.dense,NNCFLinear,weight,"[3072, 768]",2359296,235930,0.8999998569488525
193,nncf_module.bert.encoder.layer.11.output.dense,NNCFLinear,weight,"[768, 3072]",2359296,235930,0.8999998569488525