| pt_module_name,block_id,orig_w_shape,final_w_shape,orig_b_shape,final_b_shape,prune_by,id_to_keep,head_id_to_keep,nncf_graph_node | |
| nncf_module.bert.encoder.layer.0.attention.self.query,0,"(768, 768)","(256, 768)","(768,)","(256,)",group of 64 rows,See pkl,"[3, 7, 8, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.0.attention.self.key,0,"(768, 768)","(256, 768)","(768,)","(256,)",group of 64 rows,See pkl,"[3, 7, 8, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.0.attention.output.dense,0,"(768, 768)","(768, 256)","(768,)","(768,)",group of 64 cols,See pkl,"[3, 7, 8, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.0.attention.self.value,0,"(768, 768)","(256, 768)","(768,)","(256,)",group of 64 rows,See pkl,"[3, 7, 8, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.0.intermediate.dense,1,"(3072, 768)","(2199, 768)","(3072,)","(2199,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.0.output.dense,1,"(768, 3072)","(768, 2199)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.1.attention.output.dense,2,"(768, 768)","(768, 320)","(768,)","(768,)",group of 64 cols,See pkl,"[1, 4, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.1.attention.self.key,2,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[1, 4, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.1.attention.self.query,2,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[1, 4, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.1.attention.self.value,2,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[1, 4, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.1.intermediate.dense,3,"(3072, 768)","(2102, 768)","(3072,)","(2102,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.1.output.dense,3,"(768, 3072)","(768, 2102)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.2.attention.self.query,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.2.attention.output.dense,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.2.attention.self.key,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.2.attention.self.value,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.2.output.dense,5,"(768, 3072)","(768, 2304)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.2.intermediate.dense,5,"(3072, 768)","(2304, 768)","(3072,)","(2304,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.3.attention.self.value,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.3.attention.self.query,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.3.attention.output.dense,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.3.attention.self.key,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.3.intermediate.dense,7,"(3072, 768)","(2243, 768)","(3072,)","(2243,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.3.output.dense,7,"(768, 3072)","(768, 2243)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.4.attention.self.query,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.4.attention.output.dense,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.4.attention.self.key,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.4.attention.self.value,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.4.intermediate.dense,9,"(3072, 768)","(2042, 768)","(3072,)","(2042,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.4.output.dense,9,"(768, 3072)","(768, 2042)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.5.attention.self.key,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.5.attention.self.query,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.5.attention.self.value,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.5.attention.output.dense,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.5.intermediate.dense,11,"(3072, 768)","(2007, 768)","(3072,)","(2007,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.5.output.dense,11,"(768, 3072)","(768, 2007)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.6.attention.self.value,12,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 7, 8, 9, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.6.attention.self.query,12,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 7, 8, 9, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.6.attention.self.key,12,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 7, 8, 9, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.6.attention.output.dense,12,"(768, 768)","(768, 384)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 7, 8, 9, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.6.intermediate.dense,13,"(3072, 768)","(1610, 768)","(3072,)","(1610,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.6.output.dense,13,"(768, 3072)","(768, 1610)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.7.attention.output.dense,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.7.attention.self.query,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.7.attention.self.value,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.7.attention.self.key,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.7.intermediate.dense,15,"(3072, 768)","(1262, 768)","(3072,)","(1262,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.7.output.dense,15,"(768, 3072)","(768, 1262)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.8.attention.self.value,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.8.attention.self.query,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.8.attention.self.key,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.8.attention.output.dense,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.8.output.dense,17,"(768, 3072)","(768, 794)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.8.intermediate.dense,17,"(3072, 768)","(794, 768)","(3072,)","(794,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.9.attention.self.query,18,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[0, 2, 6, 8, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.9.attention.self.key,18,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[0, 2, 6, 8, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.9.attention.self.value,18,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[0, 2, 6, 8, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.9.attention.output.dense,18,"(768, 768)","(768, 320)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 2, 6, 8, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.9.intermediate.dense,19,"(3072, 768)","(305, 768)","(3072,)","(305,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.9.output.dense,19,"(768, 3072)","(768, 305)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.10.attention.self.value,20,"(768, 768)","(256, 768)","(768,)","(256,)",group of 64 rows,See pkl,"[3, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.10.attention.self.query,20,"(768, 768)","(256, 768)","(768,)","(256,)",group of 64 rows,See pkl,"[3, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.10.attention.output.dense,20,"(768, 768)","(768, 256)","(768,)","(768,)",group of 64 cols,See pkl,"[3, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.10.attention.self.key,20,"(768, 768)","(256, 768)","(768,)","(256,)",group of 64 rows,See pkl,"[3, 7, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.10.intermediate.dense,21,"(3072, 768)","(305, 768)","(3072,)","(305,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.10.output.dense,21,"(768, 3072)","(768, 305)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.11.attention.self.query,22,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 | |
| nncf_module.bert.encoder.layer.11.attention.output.dense,22,"(768, 768)","(768, 320)","(768,)","(768,)",group of 64 cols,See pkl,"[1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.11.attention.self.value,22,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 | |
| nncf_module.bert.encoder.layer.11.attention.self.key,22,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 | |
| nncf_module.bert.encoder.layer.11.intermediate.dense,23,"(3072, 768)","(364, 768)","(3072,)","(364,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 | |
| nncf_module.bert.encoder.layer.11.output.dense,23,"(768, 3072)","(768, 364)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0 | |