diff --git "a/eftnas-s1-bert-base-cola/compressed_graph.dot" "b/eftnas-s1-bert-base-cola/compressed_graph.dot"
new file mode 100644--- /dev/null
+++ "b/eftnas-s1-bert-base-cola/compressed_graph.dot"
@@ -0,0 +1,1066 @@
+strict digraph  {
+"0 /nncf_model_input_0";
+"1 /nncf_model_input_1";
+"2 /nncf_model_input_2";
+"3 BertForSequenceClassification/BertModel[bert]/__getitem___0";
+"4 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[word_embeddings]/embedding_0";
+"5 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[token_type_embeddings]/embedding_0";
+"6 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__add___0";
+"7 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[position_embeddings]/embedding_0";
+"8 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__iadd___0";
+"9 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"10 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/Dropout[dropout]/dropout_0";
+"11 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"12 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"13 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"14 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"15 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"16 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"17 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"18 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"19 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"20 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"21 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"22 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"23 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"24 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"25 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"26 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"27 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"28 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"29 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"30 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"31 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"32 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"33 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"34 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"35 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"36 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"37 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"38 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"39 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"40 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"41 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"42 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"43 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"44 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"45 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"46 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"47 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"48 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"49 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"50 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/__add___0";
+"51 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"52 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"53 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"54 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"55 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"56 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"57 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"58 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"59 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"60 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"61 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"62 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"63 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"64 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"65 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"66 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"67 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"68 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"69 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"70 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"71 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"72 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"73 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"74 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"75 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"76 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"77 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"78 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"79 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"80 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"81 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"82 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"83 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"84 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"85 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"86 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"87 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"88 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"89 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"90 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"91 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/__add___0";
+"92 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"93 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"94 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"95 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"96 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"97 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"98 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"99 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"100 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"101 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"102 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"103 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"104 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"105 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"106 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"107 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"108 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"109 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"110 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"111 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"112 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"113 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"114 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"115 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"116 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"117 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"118 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"119 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"120 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"121 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"122 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"123 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"124 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"125 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"126 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"127 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"128 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"129 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"130 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"131 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"132 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/__add___0";
+"133 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"134 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"135 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"136 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"137 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"138 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"139 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"140 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"141 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"142 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"143 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"144 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"145 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"146 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"147 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"148 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"149 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"150 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"151 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"152 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"153 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"154 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"155 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"156 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"157 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"158 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"159 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"160 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"161 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"162 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"163 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"164 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"165 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"166 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"167 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"168 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"169 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"170 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"171 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"172 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"173 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/__add___0";
+"174 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"175 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"176 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"177 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"178 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"179 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"180 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"181 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"182 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"183 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"184 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"185 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"186 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"187 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"188 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"189 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"190 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"191 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"192 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"193 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"194 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"195 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"196 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"197 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"198 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"199 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"200 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"201 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"202 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"203 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"204 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"205 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"206 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"207 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"208 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"209 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"210 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"211 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"212 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"213 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"214 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/__add___0";
+"215 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"216 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"217 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"218 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"219 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"220 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"221 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"222 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"223 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"224 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"225 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"226 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"227 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"228 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"229 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"230 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"231 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"232 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"233 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"234 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"235 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"236 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"237 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"238 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"239 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"240 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"241 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"242 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"243 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"244 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"245 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"246 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"247 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"248 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"249 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"250 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"251 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"252 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"253 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"254 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"255 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/__add___0";
+"256 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"257 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"258 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"259 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"260 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"261 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"262 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"263 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"264 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"265 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"266 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"267 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"268 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"269 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"270 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"271 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"272 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"273 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"274 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"275 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"276 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"277 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"278 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"279 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"280 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"281 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"282 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"283 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"284 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"285 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"286 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"287 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"288 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"289 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"290 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"291 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"292 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"293 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"294 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"295 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"296 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/__add___0";
+"297 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"298 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"299 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"300 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"301 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"302 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"303 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"304 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"305 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"306 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"307 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"308 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"309 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"310 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"311 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"312 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"313 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"314 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"315 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"316 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"317 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"318 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"319 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"320 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"321 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"322 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"323 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"324 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"325 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"326 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"327 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"328 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"329 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"330 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"331 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"332 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"333 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"334 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"335 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"336 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"337 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/__add___0";
+"338 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"339 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"340 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"341 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"342 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"343 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"344 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"345 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"346 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"347 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"348 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"349 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"350 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"351 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"352 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"353 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"354 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"355 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"356 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"357 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"358 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"359 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"360 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"361 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"362 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"363 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"364 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"365 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"366 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"367 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"368 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"369 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"370 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"371 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"372 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"373 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"374 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"375 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"376 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"377 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"378 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/__add___0";
+"379 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"380 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"381 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"382 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"383 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"384 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"385 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"386 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"387 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"388 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"389 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"390 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"391 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"392 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"393 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"394 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"395 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"396 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"397 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"398 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"399 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"400 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"401 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"402 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"403 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"404 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"405 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"406 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"407 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"408 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"409 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"410 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"411 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"412 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"413 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"414 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"415 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"416 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"417 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"418 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"419 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/__add___0";
+"420 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"421 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"422 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"423 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"424 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"425 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"426 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"427 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"428 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"429 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"430 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"431 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"432 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"433 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"434 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"435 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"436 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"437 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"438 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"439 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"440 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"441 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"442 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"443 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"444 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"445 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"446 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"447 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"448 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"449 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"450 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"451 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"452 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"453 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"454 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"455 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"456 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"457 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"458 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"459 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"460 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/__add___0";
+"461 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"462 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"463 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"464 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0";
+"465 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"466 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"467 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0";
+"468 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_0";
+"469 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_0";
+"470 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"471 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"472 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0";
+"473 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_1";
+"474 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_1";
+"475 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_2";
+"476 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_2";
+"477 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/transpose_0";
+"478 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_0";
+"479 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0";
+"480 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/__add___0";
+"481 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/softmax_0";
+"482 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0";
+"483 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_1";
+"484 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_3";
+"485 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0";
+"486 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_3";
+"487 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"488 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"489 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0";
+"490 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0";
+"491 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/__add___0";
+"492 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"493 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"494 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"495 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0";
+"496 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0";
+"497 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0";
+"498 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1";
+"499 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0";
+"500 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/Dropout[dropout]/dropout_0";
+"501 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/__add___0";
+"502 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0";
+"503 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/__getitem___0";
+"504 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/NNCFLinear[dense]/linear_0";
+"505 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/Tanh[activation]/tanh_0";
+"506 BertForSequenceClassification/Dropout[dropout]/dropout_0";
+"507 BertForSequenceClassification/NNCFLinear[classifier]/linear_0";
+"508 /nncf_model_output_0";
+"0 /nncf_model_input_0" -> "4 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[word_embeddings]/embedding_0"  [label="(1, 128) \n0 -> 0", style=dashed];
+"1 /nncf_model_input_1" -> "3 BertForSequenceClassification/BertModel[bert]/__getitem___0"  [label="(1, 128) \n0 -> 0", style=dashed];
+"2 /nncf_model_input_2" -> "5 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[token_type_embeddings]/embedding_0"  [label="(1, 128) \n0 -> 0", style=dashed];
+"4 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[word_embeddings]/embedding_0" -> "6 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"5 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[token_type_embeddings]/embedding_0" -> "6 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"6 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__add___0" -> "8 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__iadd___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"7 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFEmbedding[position_embeddings]/embedding_0" -> "8 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__iadd___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"8 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/__iadd___0" -> "9 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"9 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "10 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"10 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/Dropout[dropout]/dropout_0" -> "13 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"10 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/Dropout[dropout]/dropout_0" -> "16 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"10 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/Dropout[dropout]/dropout_0" -> "21 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"10 BertForSequenceClassification/BertModel[bert]/BertEmbeddings[embeddings]/Dropout[dropout]/dropout_0" -> "40 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"11 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "13 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"12 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "13 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"13 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "24 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"14 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "16 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"15 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "16 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"16 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "17 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"17 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "18 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"18 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "26 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"19 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "21 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"20 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "21 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"21 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "22 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"22 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "23 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"23 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "32 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"24 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "25 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"25 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "27 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"26 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "27 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"27 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "28 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"28 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "29 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"29 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "30 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"30 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "31 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"31 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "32 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"32 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "33 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"33 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "34 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"34 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "35 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"35 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "38 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"36 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "38 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"37 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "38 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"38 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "39 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"39 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "40 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"40 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "41 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"41 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "44 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"41 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "50 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"42 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "44 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"43 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "44 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"44 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "45 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"45 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "48 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"46 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "48 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"47 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "48 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"48 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "49 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"49 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "50 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"50 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/__add___0" -> "51 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"51 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "54 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"51 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "57 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"51 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "62 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"51 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "81 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"52 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "54 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"53 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "54 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"54 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "65 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"55 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "57 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"56 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "57 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"57 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "58 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"58 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "59 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"59 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "67 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"60 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "62 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"61 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "62 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"62 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "63 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"63 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "64 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"64 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "73 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"65 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "66 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"66 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "68 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"67 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "68 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"68 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "69 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"69 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "70 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"70 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "71 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"71 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "72 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"72 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "73 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"73 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "74 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"74 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "75 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"75 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "76 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"76 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "79 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"77 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "79 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"78 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "79 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"79 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "80 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"80 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "81 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"81 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "82 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"82 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "85 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"82 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "91 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"83 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "85 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"84 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "85 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"85 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "86 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"86 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "89 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"87 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "89 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"88 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "89 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"89 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "90 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"90 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "91 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"91 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/__add___0" -> "92 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"92 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "95 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"92 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "98 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"92 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "103 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"92 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "122 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"93 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "95 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"94 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "95 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"95 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "106 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"96 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "98 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"97 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "98 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"98 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "99 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"99 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "100 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"100 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "108 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"101 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "103 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"102 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "103 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"103 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "104 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"104 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "105 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"105 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "114 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"106 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "107 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"107 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "109 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"108 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "109 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"109 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "110 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"110 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "111 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"111 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "112 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"112 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "113 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"113 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "114 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"114 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "115 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"115 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "116 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"116 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "117 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"117 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "120 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"118 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "120 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"119 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "120 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"120 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "121 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"121 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "122 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"122 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "123 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"123 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "126 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"123 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "132 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"124 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "126 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"125 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "126 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"126 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "127 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"127 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "130 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"128 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "130 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"129 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "130 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"130 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "131 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"131 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "132 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"132 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/__add___0" -> "133 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"133 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "136 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"133 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "139 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"133 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "144 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"133 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "163 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"134 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "136 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"135 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "136 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"136 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "147 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"137 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "139 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"138 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "139 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"139 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "140 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"140 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "141 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"141 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "149 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"142 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "144 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"143 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "144 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"144 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "145 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"145 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "146 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"146 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "155 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"147 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "148 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"148 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "150 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"149 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "150 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"150 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "151 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"151 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "152 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"152 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "153 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"153 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "154 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"154 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "155 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"155 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "156 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"156 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "157 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"157 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "158 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"158 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "161 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"159 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "161 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"160 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "161 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"161 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "162 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"162 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "163 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"163 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "164 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"164 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "167 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"164 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "173 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"165 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "167 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"166 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "167 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"167 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "168 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"168 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "171 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"169 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "171 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"170 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "171 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"171 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "172 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"172 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "173 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"173 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/__add___0" -> "174 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"174 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "177 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"174 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "180 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"174 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "185 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"174 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "204 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"175 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "177 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"176 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "177 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"177 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "188 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"178 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "180 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"179 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "180 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"180 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "181 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"181 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "182 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"182 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "190 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"183 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "185 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"184 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "185 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"185 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "186 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"186 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "187 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"187 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "196 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"188 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "189 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"189 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "191 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"190 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "191 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"191 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "192 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"192 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "193 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"193 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "194 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"194 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "195 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"195 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "196 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"196 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "197 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"197 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "198 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"198 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "199 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"199 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "202 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"200 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "202 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"201 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "202 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"202 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "203 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"203 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "204 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"204 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "205 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"205 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "208 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"205 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "214 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"206 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "208 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"207 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "208 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"208 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "209 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"209 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "212 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"210 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "212 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"211 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "212 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"212 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "213 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"213 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "214 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"214 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/__add___0" -> "215 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"215 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "218 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"215 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "221 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"215 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "226 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"215 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "245 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"216 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "218 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"217 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "218 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"218 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "229 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"219 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "221 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"220 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "221 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"221 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "222 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"222 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "223 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"223 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "231 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"224 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "226 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"225 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "226 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"226 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "227 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"227 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "228 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"228 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "237 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"229 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "230 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"230 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "232 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"231 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "232 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"232 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "233 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"233 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "234 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"234 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "235 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"235 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "236 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"236 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "237 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"237 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "238 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"238 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "239 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"239 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "240 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"240 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "243 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"241 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "243 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"242 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "243 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"243 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "244 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"244 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "245 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"245 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "246 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"246 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "249 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"246 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "255 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"247 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "249 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"248 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "249 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"249 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "250 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"250 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "253 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"251 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "253 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"252 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "253 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"253 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "254 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"254 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "255 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"255 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/__add___0" -> "256 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"256 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "259 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"256 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "262 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"256 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "267 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"256 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "286 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"257 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "259 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"258 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "259 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"259 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "270 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"260 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "262 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"261 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "262 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"262 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "263 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"263 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "264 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"264 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "272 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"265 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "267 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"266 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "267 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"267 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "268 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"268 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "269 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"269 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "278 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"270 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "271 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"271 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "273 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"272 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "273 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"273 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "274 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"274 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "275 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"275 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "276 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"276 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "277 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"277 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "278 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"278 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "279 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"279 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "280 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"280 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "281 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"281 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "284 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"282 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "284 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"283 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "284 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"284 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "285 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"285 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "286 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"286 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "287 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"287 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "290 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"287 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "296 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"288 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "290 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"289 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "290 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"290 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "291 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"291 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "294 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"292 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "294 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"293 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "294 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"294 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "295 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"295 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "296 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"296 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/__add___0" -> "297 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"297 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "300 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"297 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "303 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"297 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "308 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"297 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "327 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"298 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "300 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"299 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "300 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"300 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "311 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"301 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "303 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"302 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "303 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"303 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "304 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"304 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "305 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"305 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "313 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"306 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "308 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"307 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "308 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"308 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "309 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"309 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "310 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"310 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "319 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"311 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "312 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"312 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "314 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"313 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "314 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"314 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "315 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"315 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "316 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"316 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "317 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"317 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "318 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"318 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "319 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"319 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "320 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"320 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "321 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"321 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "322 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"322 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "325 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"323 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "325 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"324 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "325 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"325 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "326 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"326 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "327 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"327 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "328 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"328 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "331 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"328 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "337 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"329 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "331 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"330 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "331 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"331 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "332 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"332 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "335 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"333 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "335 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"334 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "335 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"335 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "336 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"336 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "337 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"337 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/__add___0" -> "338 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"338 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "341 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"338 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "344 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"338 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "349 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"338 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "368 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"339 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "341 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"340 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "341 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"341 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "352 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"342 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "344 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"343 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "344 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"344 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "345 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"345 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "346 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"346 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "354 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"347 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "349 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"348 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "349 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"349 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "350 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"350 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "351 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"351 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "360 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"352 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "353 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"353 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "355 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"354 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "355 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"355 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "356 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"356 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "357 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"357 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "358 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"358 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "359 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"359 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "360 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"360 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "361 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"361 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "362 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"362 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "363 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"363 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "366 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"364 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "366 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"365 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "366 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"366 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "367 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"367 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "368 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"368 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "369 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"369 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "372 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"369 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "378 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"370 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "372 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"371 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "372 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"372 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "373 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"373 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "376 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"374 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "376 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"375 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "376 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"376 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "377 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"377 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "378 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"378 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/__add___0" -> "379 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"379 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "382 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"379 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "385 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"379 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "390 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"379 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "409 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"380 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "382 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"381 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "382 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"382 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "393 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"383 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "385 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"384 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "385 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"385 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "386 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"386 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "387 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"387 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "395 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"388 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "390 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"389 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "390 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"390 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "391 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"391 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "392 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"392 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "401 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"393 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "394 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"394 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "396 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"395 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "396 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"396 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "397 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"397 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "398 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"398 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "399 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"399 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "400 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"400 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "401 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"401 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "402 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"402 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "403 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"403 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "404 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"404 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "407 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"405 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "407 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"406 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "407 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"407 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "408 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"408 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "409 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"409 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "410 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"410 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "413 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"410 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "419 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"411 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "413 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"412 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "413 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"413 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "414 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"414 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "417 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"415 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "417 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"416 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "417 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"417 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "418 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"418 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "419 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"419 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/__add___0" -> "420 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"420 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "423 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"420 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "426 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"420 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "431 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"420 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "450 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"421 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "423 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"422 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "423 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"423 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "434 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"424 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "426 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"425 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "426 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"426 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "427 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"427 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "428 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"428 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "436 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"429 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "431 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"430 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "431 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"431 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "432 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"432 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "433 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"433 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "442 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"434 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "435 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"435 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "437 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"436 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "437 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"437 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "438 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"438 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "439 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"439 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "440 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"440 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "441 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"441 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "442 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"442 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "443 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"443 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "444 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"444 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "445 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"445 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "448 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"446 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "448 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"447 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "448 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"448 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "449 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"449 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "450 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"450 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "451 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"451 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "454 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"451 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "460 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"452 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "454 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"453 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "454 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"454 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "455 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"455 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "458 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"456 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "458 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"457 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "458 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"458 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "459 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"459 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "460 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"460 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/__add___0" -> "461 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"461 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "464 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"461 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "467 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"461 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "472 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"461 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "491 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"462 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "464 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"463 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "464 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"464 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0" -> "475 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_2"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"465 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "467 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"466 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "467 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"467 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0" -> "468 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"468 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_0" -> "469 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"469 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_0" -> "477 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/transpose_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"470 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "472 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"471 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "472 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"472 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0" -> "473 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_1"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"473 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_1" -> "474 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_1"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"474 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_1" -> "483 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 64) \n0 -> 1", style=solid];
+"475 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_2" -> "476 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_2"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"476 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_2" -> "478 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"477 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/transpose_0" -> "478 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_0"  [label="(1, 12, 64, 128) \n0 -> 1", style=solid];
+"478 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_0" -> "479 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"479 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/__truediv___0" -> "480 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/__add___0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"480 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/__add___0" -> "481 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/softmax_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"481 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/softmax_0" -> "482 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"482 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/Dropout[dropout]/dropout_0" -> "483 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_1"  [label="(1, 12, 128, 128) \n0 -> 0", style=solid];
+"483 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/matmul_1" -> "484 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_3"  [label="(1, 12, 128, 64) \n0 -> 0", style=solid];
+"484 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/permute_3" -> "485 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"485 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/contiguous_0" -> "486 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_3"  [label="(1, 128, 12, 64) \n0 -> 0", style=solid];
+"486 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/view_3" -> "489 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"487 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "489 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 768) \n0 -> 1", style=solid];
+"488 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "489 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"489 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0" -> "490 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"490 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/Dropout[dropout]/dropout_0" -> "491 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"491 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/__add___0" -> "492 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"492 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "495 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"492 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "501 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 1", style=solid];
+"493 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "495 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072, 768) \n0 -> 1", style=solid];
+"494 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "495 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0"  [label="(3072,) \n0 -> 2", style=solid];
+"495 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" -> "496 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"496 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/GELUActivation[intermediate_act_fn]/gelu_0" -> "499 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(1, 128, 3072) \n0 -> 0", style=solid];
+"497 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_0" -> "499 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768, 3072) \n0 -> 1", style=solid];
+"498 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/ModuleDict[pre_ops]/UpdateWeightAndBias[0]/MovementSparsifier[op]/apply_binary_mask_1" -> "499 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0"  [label="(768,) \n0 -> 2", style=solid];
+"499 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0" -> "500 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/Dropout[dropout]/dropout_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"500 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/Dropout[dropout]/dropout_0" -> "501 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/__add___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"501 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/__add___0" -> "502 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"502 BertForSequenceClassification/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLayerNorm[LayerNorm]/layer_norm_0" -> "503 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/__getitem___0"  [label="(1, 128, 768) \n0 -> 0", style=solid];
+"503 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/__getitem___0" -> "504 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/NNCFLinear[dense]/linear_0"  [label="(1, 768) \n0 -> 0", style=solid];
+"504 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/NNCFLinear[dense]/linear_0" -> "505 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/Tanh[activation]/tanh_0"  [label="(1, 768) \n0 -> 0", style=solid];
+"505 BertForSequenceClassification/BertModel[bert]/BertPooler[pooler]/Tanh[activation]/tanh_0" -> "506 BertForSequenceClassification/Dropout[dropout]/dropout_0"  [label="(1, 768) \n0 -> 0", style=solid];
+"506 BertForSequenceClassification/Dropout[dropout]/dropout_0" -> "507 BertForSequenceClassification/NNCFLinear[classifier]/linear_0"  [label="(1, 768) \n0 -> 0", style=solid];
+"507 BertForSequenceClassification/NNCFLinear[classifier]/linear_0" -> "508 /nncf_model_output_0"  [label="(1, 2) \n0 -> 0", style=solid];
+}