diff --git "a/openvino_decoder_model.xml" "b/openvino_decoder_model.xml"
--- "a/openvino_decoder_model.xml"
+++ "b/openvino_decoder_model.xml"
@@ -1,7 +1,7 @@
 <?xml version="1.0"?>
 <net name="Model3" version="11">
 	<layers>
-		<layer id="1" name="decoder_input_ids" type="Parameter" version="opset1">
+		<layer id="3" name="decoder_input_ids" type="Parameter" version="opset1">
 			<data shape="?,?" element_type="i64" />
 			<output>
 				<port id="0" precision="I64" names="input_ids">
@@ -10,50 +10,48 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="0" name="Parameter_26736" type="Parameter" version="opset1">
-			<data shape="?,?,?" element_type="f32" />
+		<layer id="2" name="Parameter_26181" type="Parameter" version="opset1">
+			<data shape="?,?,1280" element_type="f32" />
 			<output>
 				<port id="0" precision="FP32" names="encoder_hidden_states">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="2" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="0" size="3276800" />
+		<layer id="1" name="cache_position" type="Parameter" version="opset1">
+			<data shape="?" element_type="i64" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64" names="cache_position">
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="3" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
+		<layer id="0" name="beam_idx" type="Parameter" version="opset1">
+			<data shape="?" element_type="i32" />
+			<output>
+				<port id="0" precision="I32" names="beam_idx">
+					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="4" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="0" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="4" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="5" name="__module.model.model.decoder.layers.0.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1280</dim>
@@ -61,173 +59,162 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="183,tensor.9">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="5" name="Constant_31919_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="3276800" size="2560" />
+		<layer id="6" name="Constant_32954" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="6" name="Constant_31919" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="7" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="2" precision="FP32" names="185">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="7" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="8" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>20</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I32">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="308,tensor">
+				<port id="2" precision="FP32" names="186">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="8" name="ShapeOf_32167" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
+		<layer id="10" name="ReadValue_35465" type="ReadValue" version="opset6">
+			<data variable_id="186" variable_type="dynamic" variable_shape="..." />
 			<input>
-				<port id="0" precision="I64">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="I64">
-					<dim>2</dim>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="9" name="Constant_32168" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="3279360" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="12" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="6553648" size="6553600" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="10" name="Constant_32169" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="3279360" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="11" name="Gather_32170" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="13" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>2</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="3" precision="I64" names="107,161,236,290,77">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="12" name="Constant_24866" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="3279368" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="13" name="Constant_24867" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="3279376" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="14" name="Constant_32345" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="13107248" size="5120" />
 			<output>
-				<port id="0" precision="I64">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="14" name="Constant_24868" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="3279384" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64">
 					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="15" name="__module.model.model.decoder.layers.0.self_attn/prim::ListConstruct_1" type="Concat" version="opset1">
-			<data axis="0" />
+		<layer id="15" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="2" precision="I64">
+				<port id="1" precision="FP32">
 					<dim>1</dim>
-				</port>
-				<port id="3" precision="I64">
 					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="4" precision="I64">
+				<port id="2" precision="FP32" names="306,tensor">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Constant_32963" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
+			<output>
+				<port id="0" precision="I64">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="16" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="17" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -239,7 +226,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="310">
+				<port id="2" precision="FP32" names="308">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -247,15 +234,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="17" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="18" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="18" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+		<layer id="19" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -268,7 +255,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.1.encoder.value">
+				<port id="2" precision="FP32" names="309">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -276,40 +263,41 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="20" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="3279408" size="3276800" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="21" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="20" name="ReadValue_35463" type="ReadValue" version="opset6">
+			<data variable_id="309" variable_type="dynamic" variable_shape="..." />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
 				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="13112368" size="6553600" />
+			<output>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="22" name="__module.model.model.decoder.layers.1.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="23" name="__module.model.model.decoder.layers.1.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1280</dim>
@@ -317,15 +305,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="301,tensor.21">
+				<port id="2" precision="FP32" names="299,tensor.21">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="23" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="24" name="Constant_32962" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -337,7 +333,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="303">
+				<port id="2" precision="FP32" names="301">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -345,15 +341,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="24" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="26" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="25" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+		<layer id="27" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -366,7 +362,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.1.encoder.key">
+				<port id="2" precision="FP32" names="302">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -374,769 +370,486 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="27" name="self.model.model.decoder.embed_tokens.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="51865, 1280" offset="6556208" size="132774400" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.embed_tokens.weight">
-					<dim>51865</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="28" name="self.model.model.decoder.embed_tokens.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="28" name="ReadValue_35461" type="ReadValue" version="opset6">
+			<data variable_id="302" variable_type="dynamic" variable_shape="..." />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>51865</dim>
-					<dim>1280</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
 				<port id="1" precision="FP32">
-					<dim>51865</dim>
-					<dim>1280</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="29" name="Constant_32237" type="Const" version="opset1">
-			<data element_type="i64" shape="2" offset="139330608" size="16" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="30" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="19665968" size="6553600" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>2</dim>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="30" name="__module.model.model.decoder/aten::view/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="31" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="I64">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>2</dim>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I64" names="58">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="31" name="__module.model.model.decoder.embed_tokens/aten::embedding/Convert" type="Convert" version="opset1">
-			<data destination_type="i32" />
+		<layer id="32" name="Constant_32331" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="26219568" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I64">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
+				<port id="2" precision="FP32" names="190,tensor.11">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="32" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="139330624" size="4" />
+		<layer id="34" name="Constant_32955" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="33" name="__module.model.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="35" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>51865</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="I32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
-				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="3" precision="FP32" names="60,inputs_embeds">
+				<port id="2" precision="FP32" names="192">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>20</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="34" name="self.model.model.decoder.embed_positions.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="448, 1280" offset="139330628" size="1146880" />
+		<layer id="36" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.embed_positions.weight">
-					<dim>448</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I32">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="35" name="self.model.model.decoder.embed_positions.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>448</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>448</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="36" name="35" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="3279360" size="8" />
-			<output>
-				<port id="0" precision="I64" names="35" />
-			</output>
-		</layer>
-		<layer id="37" name="Constant_32154" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="140477508" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="38" name="Constant_32155" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="3279360" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="39" name="Gather_32156" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>2</dim>
-				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I64" />
-			</input>
-			<output>
-				<port id="3" precision="I64" names="55,61,71,73" />
-			</output>
-		</layer>
-		<layer id="40" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="140477516" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="41" name="__module.model.model.decoder/aten::arange/Range" type="Range" version="opset4">
-			<data output_type="f32" />
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
-			<output>
-				<port id="3" precision="FP32" names="63,cache_position">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="42" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
+		<layer id="37" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I64" />
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="64,position_ids">
-					<dim>1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="43" name="__module.model.model.decoder.embed_positions/aten::index/Convert" type="Convert" version="opset1">
-			<data destination_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>1</dim>
 					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I32">
-					<dim>1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="44" name="__module.model.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="139330624" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="45" name="__module.model.model.decoder.embed_positions/aten::index/Gather" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>448</dim>
-					<dim>1280</dim>
+					<dim>20</dim>
+					<dim>64</dim>
 				</port>
 				<port id="1" precision="I32">
-					<dim>1</dim>
-					<dim>-1</dim>
+					<dim>4</dim>
 				</port>
-				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="3" precision="FP32" names="67,68,positions,positions.1">
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="193">
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="46" name="__module.model.model.decoder/aten::add/Add_1" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="38" name="ReadValue_35459" type="ReadValue" version="opset6">
+			<data variable_id="193" variable_type="dynamic" variable_shape="..." />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="69,input.1">
+				<port id="1" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="47" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="40" name="Constant_35029" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
+				<port id="0" precision="FP32" />
 			</output>
 		</layer>
-		<layer id="48" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="41" name="ShapeOf_35015" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
 			<input>
-				<port id="0" precision="FP32">
+				<port id="0" precision="I64">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I64">
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="49" name="Constant_31920_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="140477524" size="2560" />
+		<layer id="42" name="Constant_35017" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="50" name="Constant_31920" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="43" name="Constant_35019" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="51" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="44" name="Gather_35020" type="Gather" version="opset8">
+			<data batch_dims="0" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>2</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
+				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="3" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="52" name="Constant_31921_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="140480084" size="2560" />
+		<layer id="45" name="Constant_35022" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224700" size="8" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="53" name="Constant_31921" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+		<layer id="46" name="Constant_35024" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
+			<output>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="47" name="Constant_35026" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224708" size="8" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="54" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="48" name="Concat_35027" type="Concat" version="opset1">
+			<data axis="0" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="1" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="2" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="102,hidden_states.1">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="3" precision="I64">
+					<dim>1</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="55" name="Constant_31822_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="140482644" size="3276800" />
+			</input>
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="4" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="56" name="Constant_31822" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="49" name="Broadcast_35030" type="Broadcast" version="opset3">
+			<data mode="numpy" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="FP32" />
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="57" name="Multiply_31805" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="50" name="ReadValue_34631" type="ReadValue" version="opset6">
+			<data variable_id="past_key_values.1.decoder.valuepresent.1.decoder.value" variable_type="f32" variable_shape="?,20,?,64" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="1" precision="FP32" names="past_key_values.1.decoder.value">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="58" name="Constant_31922_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="143759444" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="59" name="Constant_31922" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="51" name="Constant_34241" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="60" name="__module.model.model.decoder.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="52" name="Gather_34242" type="Gather" version="opset8">
+			<data batch_dims="0" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
 				</port>
+				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="112,tensor.1">
+				<port id="3" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="53" name="self.model.model.decoder.embed_tokens.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="51865, 1280" offset="26224716" size="265548800" />
+			<output>
+				<port id="0" precision="FP32" names="self.model.model.decoder.embed_tokens.weight">
+					<dim>51865</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="61" name="Constant_32238" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="54" name="__module.model.model.decoder/prim::ListConstruct" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="291773516" size="16" />
 			<output>
 				<port id="0" precision="I64">
-					<dim>4</dim>
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="62" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+		<layer id="55" name="__module.model.model.decoder/aten::view/Reshape" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
-				<port id="0" precision="FP32">
+				<port id="0" precision="I64">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
 				<port id="1" precision="I64">
-					<dim>4</dim>
+					<dim>2</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="114">
+				<port id="2" precision="I64" names="69">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="63" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="64" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+		<layer id="56" name="__module.model.model.decoder.embed_tokens/aten::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="i32" />
 			<input>
-				<port id="0" precision="FP32">
+				<port id="0" precision="I64">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="115">
+				<port id="1" precision="I32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="65" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="143762036" size="3276800" />
+		<layer id="57" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.self_attn.k_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="66" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="58" name="__module.model.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
+				<port id="0" precision="FP32">
+					<dim>51865</dim>
 					<dim>1280</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="67" name="__module.model.model.decoder.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="I32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
 				</port>
+				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="118,tensor.3">
+				<port id="3" precision="FP32" names="71,inputs_embeds">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="68" name="Constant_32239" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="59" name="self.model.model.decoder.embed_positions.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="448, 1280" offset="291773532" size="2293760" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="69" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="0" precision="FP32" names="self.model.model.decoder.embed_positions.weight">
+					<dim>448</dim>
 					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>4</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="120">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
-				</port>
 			</output>
 		</layer>
-		<layer id="70" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="60" name="45" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>4</dim>
-				</port>
+				<port id="0" precision="I64" names="45" />
 			</output>
 		</layer>
-		<layer id="71" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+		<layer id="61" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="I64">
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
+				<port id="1" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.0.decoder.key">
-					<dim>-1</dim>
-					<dim>20</dim>
+				<port id="2" precision="I64" names="72">
+					<dim>1</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="72" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="62" name="ShapeOf_32739" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>64</dim>
-				</port>
-				<port id="1" precision="FP32">
+				<port id="0" precision="I64">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="131,attn_weights.1">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="1" precision="I64">
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="73" name="__module.model.model.decoder/aten::triu/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="139330624" size="4" />
+		<layer id="63" name="Constant_32740" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="74" name="29" type="Const" version="opset1">
-			<data element_type="f32" shape="" offset="147038836" size="4" />
+		<layer id="64" name="Constant_32741" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
 			<output>
-				<port id="0" precision="FP32" names="29" />
+				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="75" name="Constant_32177" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="140477508" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
+		<layer id="65" name="Gather_32742" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
 				<port id="0" precision="I64">
-					<dim>1</dim>
+					<dim>2</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="76" name="Reshape_32178" type="Reshape" version="opset1">
-			<data special_zero="false" />
-			<input>
-				<port id="0" precision="I64" />
 				<port id="1" precision="I64">
 					<dim>1</dim>
 				</port>
+				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="I64">
+				<port id="3" precision="I64" names="118,173,237,289,66,89">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="77" name="__module.model.model.decoder/aten::add/Multiply_3" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="140477508" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="66" name="Constant_26486" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
 			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="78" name="__module.model.model.decoder/aten::add/Add_3" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64" />
-			</input>
-			<output>
-				<port id="2" precision="I64" names="74,76" />
-			</output>
-		</layer>
-		<layer id="79" name="Constant_24581" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="139330624" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="80" name="Unsqueeze_24582" type="Unsqueeze" version="opset1">
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I64">
+				<port id="0" precision="I64">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="81" name="__module.model.model.decoder/prim::ListConstruct_1" type="Concat" version="opset1">
+		<layer id="67" name="__module.model.model.decoder/prim::ListConstruct/Concat" type="Concat" version="opset1">
 			<data axis="0" />
 			<input>
 				<port id="0" precision="I64">
@@ -1147,412 +860,565 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I64">
+				<port id="2" precision="I64" names="73">
 					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="82" name="__module.model.model.decoder/aten::full/Broadcast" type="Broadcast" version="opset3">
-			<data mode="numpy" />
+		<layer id="68" name="__module.model.model.decoder/aten::repeat/Tile" type="Tile" version="opset1">
 			<input>
-				<port id="0" precision="FP32" />
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
 				<port id="1" precision="I64">
 					<dim>2</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="79">
+				<port id="2" precision="I64" names="74,position_ids">
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="83" name="ShapeOf_32184" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="69" name="__module.model.model.decoder.embed_positions/aten::index/Convert" type="Convert" version="opset1">
+			<data destination_type="i32" />
 			<input>
-				<port id="0" precision="FP32">
+				<port id="0" precision="I64">
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</input>
 			<output>
 				<port id="1" precision="I32">
-					<dim>2</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="84" name="Constant_32185" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="140477508" size="8" />
+		<layer id="70" name="__module.model.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="0" precision="I64" />
+				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="85" name="Constant_32186" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="3279360" size="8" />
+		<layer id="71" name="__module.model.model.decoder.embed_positions/aten::index/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>448</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
 			<output>
-				<port id="0" precision="I64" />
+				<port id="3" precision="FP32" names="77,78,positions,positions.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="86" name="Gather_32187" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="72" name="__module.model.model.decoder/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I32">
-					<dim>2</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="3" precision="I32" />
+				<port id="2" precision="FP32" names="79,input.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="87" name="__module.model.model.decoder/aten::triu/Constant_2" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="140477516" size="4" />
+		<layer id="73" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="88" name="__module.model.model.decoder/aten::triu/Range" type="Range" version="opset4">
-			<data output_type="i32" />
+		<layer id="74" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32" />
-				<port id="2" precision="I32" />
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>1</dim>
+				</port>
 			</input>
 			<output>
-				<port id="3" precision="I32">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="75" name="Constant_32322" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="294067304" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="89" name="__module.model.model.decoder/aten::triu/Unsqueeze" type="Unsqueeze" version="opset1">
+		<layer id="76" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I32" />
 			</input>
 			<output>
-				<port id="2" precision="I32">
-					<dim>1</dim>
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="90" name="__module.model.model.decoder/aten::triu/Convert" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="140477516" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="91" name="Convert_32190" type="Convert" version="opset1">
-			<data destination_type="i32" />
-			<input>
-				<port id="0" precision="I64" />
-			</input>
+		<layer id="77" name="Constant_32323" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="294072424" size="5120" />
 			<output>
-				<port id="1" precision="I32" />
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="92" name="__module.model.model.decoder/aten::triu/Add" type="Add" version="opset1">
+		<layer id="78" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32" />
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
 			</input>
 			<output>
-				<port id="2" precision="I32" />
+				<port id="2" precision="FP32" names="113,hidden_states.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="93" name="__module.model.model.decoder/aten::triu/Range_1" type="Range" version="opset4">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32" />
-				<port id="2" precision="I32" />
-			</input>
+		<layer id="79" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="294077544" size="6553600" />
 			<output>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.self_attn.q_proj.weight">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="94" name="__module.model.model.decoder/aten::triu/Unsqueeze_1" type="Unsqueeze" version="opset1">
+		<layer id="80" name="__module.model.model.decoder.layers.0.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I32" />
 			</input>
 			<output>
-				<port id="2" precision="I32">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="81" name="Constant_32324" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="300631144" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="95" name="__module.model.model.decoder/aten::triu/GreaterEqual" type="GreaterEqual" version="opset1">
+		<layer id="82" name="__module.model.model.decoder.layers.0.self_attn.q_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I32">
-					<dim>1</dim>
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
 					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="BOOL">
+				<port id="2" precision="FP32" names="122,tensor.1">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="96" name="__module.model.model.decoder/aten::triu/ConvertLike_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="" offset="147038840" size="2" />
+		<layer id="83" name="Constant_32949" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
-				<port id="0" precision="FP16" />
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="97" name="__module.model.model.decoder/aten::triu/ConvertLike" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="84" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
-				<port id="0" precision="FP16" />
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" />
+				<port id="2" precision="FP32" names="124">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="98" name="__module.model.model.decoder/aten::triu/Select" type="Select" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="85" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="86" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
 			<input>
-				<port id="0" precision="BOOL">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="1" precision="I32">
+					<dim>4</dim>
 				</port>
-				<port id="2" precision="FP32" />
 			</input>
 			<output>
-				<port id="3" precision="FP32" names="80_1">
+				<port id="2" precision="FP32" names="125">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="99" name="__module.model.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="139330624" size="4" />
+		<layer id="87" name="Constant_35041" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="FP32" />
 			</output>
 		</layer>
-		<layer id="100" name="__module.model.model.decoder/aten::arange/Constant_2" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="140477516" size="4" />
+		<layer id="88" name="Constant_35034" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224700" size="8" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="101" name="__module.model.model.decoder/aten::arange/Range_1" type="Range" version="opset4">
-			<data output_type="f32" />
-			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
+		<layer id="89" name="Constant_35036" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
 			<output>
-				<port id="3" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="102" name="__module.model.model.decoder/aten::arange/ConvertLike" type="Convert" version="opset1">
-			<data destination_type="i64" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-				</port>
-			</input>
+		<layer id="90" name="Constant_35038" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224708" size="8" />
 			<output>
-				<port id="1" precision="I64" names="81">
-					<dim>-1</dim>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="103" name="__module.model.model.decoder/aten::gt/Convert" type="Convert" version="opset1">
-			<data destination_type="f32" />
+		<layer id="91" name="Concat_35039" type="Concat" version="opset1">
+			<data axis="0" />
 			<input>
 				<port id="0" precision="I64">
-					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="2" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="3" precision="I64">
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
+				<port id="4" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="104" name="Constant_24684" type="Const" version="opset1">
-			<data element_type="i64" shape="2" offset="147038842" size="16" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="92" name="Broadcast_35042" type="Broadcast" version="opset3">
+			<data mode="numpy" />
+			<input>
+				<port id="0" precision="FP32" />
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I64" names="82">
-					<dim>2</dim>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="105" name="__module.model.model.decoder/aten::reshape/Reshape" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="93" name="ReadValue_34625" type="ReadValue" version="opset6">
+			<data variable_id="past_key_values.0.decoder.keypresent.0.decoder.key" variable_type="f32" variable_shape="?,20,?,64" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>2</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="83">
+				<port id="1" precision="FP32" names="past_key_values.0.decoder.key">
 					<dim>-1</dim>
-					<dim>1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="106" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="94" name="Constant_34232" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="95" name="Gather_34233" type="Gather" version="opset8">
+			<data batch_dims="0" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="1" precision="I32">
 					<dim>-1</dim>
-					<dim>1</dim>
 				</port>
+				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="BOOL" names="84">
+				<port id="3" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="107" name="__module.model.model.decoder/aten::mul_/ConvertLike" type="Convert" version="opset1">
-			<data destination_type="f32" />
+		<layer id="96" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="300636264" size="6553600" />
+			<output>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.self_attn.k_proj.weight">
+					<dim>1280</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="97" name="__module.model.model.decoder.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="BOOL">
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="2" precision="FP32" names="128,tensor.3">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="108" name="__module.model.model.decoder/aten::mul_/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="98" name="Constant_32950" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="99" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="80,causal_mask.1">
+				<port id="2" precision="FP32" names="130">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="100" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="109" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
+		<layer id="101" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
 				</port>
-				<port id="1" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="86">
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="131">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="110" name="40" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="140477508" size="8" />
-			<output>
-				<port id="0" precision="I64" names="40" />
-			</output>
-		</layer>
-		<layer id="111" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_2" type="Unsqueeze" version="opset1">
+		<layer id="102" name="__module.model.model.decoder.layers.0.self_attn/aten::cat/Concat" type="Concat" version="opset1">
+			<data axis="-2" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>1</dim>
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="87,88,89">
-					<dim>1</dim>
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="key_states.7">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="112" name="Constant_31154" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="140477508" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="103" name="Constant_35053" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="26224688" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="104" name="Constant_35046" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224700" size="8" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="113" name="Constant_31156" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="140477508" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="105" name="Constant_35048" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="114" name="Constant_31158" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="140477508" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="106" name="Constant_35050" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224708" size="8" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="115" name="__module.model.model.decoder/prim::ListConstruct_2" type="Concat" version="opset1">
+		<layer id="107" name="Concat_35051" type="Concat" version="opset1">
 			<data axis="0" />
 			<input>
 				<port id="0" precision="I64">
@@ -1574,798 +1440,794 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="116" name="__module.model.model.decoder/aten::expand/Broadcast" type="Broadcast" version="opset3">
-			<data mode="bidirectional" />
+		<layer id="108" name="Broadcast_35054" type="Broadcast" version="opset3">
+			<data mode="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
+				<port id="0" precision="FP32" />
 				<port id="1" precision="I64">
 					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="133,134,135,262,263,264,91,attention_mask">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>1</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="109" name="ReadValue_34627" type="ReadValue" version="opset6">
+			<data variable_id="past_key_values.0.decoder.valuepresent.0.decoder.value" variable_type="f32" variable_shape="?,20,?,64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="past_key_values.0.decoder.value">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="117" name="Constant_25118" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="3279360" size="8" />
+		<layer id="110" name="Constant_34235" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
+				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="118" name="ShapeOf_32199" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
+		<layer id="111" name="Gather_34236" type="Gather" version="opset8">
+			<data batch_dims="0" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="1" precision="I64">
-					<dim>3</dim>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="119" name="Constant_32200" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="140477508" size="8" />
+		<layer id="112" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="307189864" size="6553600" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.self_attn.v_proj.weight">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="120" name="Constant_32201" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="3279360" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="121" name="Gather_32202" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="113" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>3</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="3" precision="I64" names="132,261">
-					<dim>1</dim>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="122" name="Constant_25121" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="140477508" size="8" />
+		<layer id="114" name="Constant_32325" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="313743464" size="5120" />
 			<output>
-				<port id="0" precision="I64">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="123" name="__module.model.model.decoder/aten::slice/Reshape_1" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="147038858" size="8" />
-			<output>
-				<port id="0" precision="I64">
 					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="124" name="__module.model.model.decoder.layers.0.self_attn/aten::slice/Slice_3" type="Slice" version="opset8">
+		<layer id="115" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="3" precision="I64">
+				<port id="1" precision="FP32">
 					<dim>1</dim>
-				</port>
-				<port id="4" precision="I64">
 					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="5" precision="FP32" names="136,265,causal_mask,causal_mask.5">
-					<dim>-1</dim>
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="135,tensor.5">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="125" name="__module.model.model.decoder.layers.0.self_attn/aten::add/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="116" name="Constant_32951" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="117" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="137">
 					<dim>-1</dim>
-					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="118" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="119" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="137,input.3">
+				<port id="2" precision="FP32" names="138">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="126" name="__module.model.model.decoder.layers.0.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
-			<data axis="-1" />
+		<layer id="120" name="__module.model.model.decoder.layers.0.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
+			<data axis="-2" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="138,input.5">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="127" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="147038866" size="3276800" />
+		<layer id="121" name="Constant_32326" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1" offset="313748584" size="4" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.self_attn.v_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="128" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="122" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="129" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="123" name="ShapeOf_32755" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="130" name="Constant_31923_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="150315666" size="2560" />
+		<layer id="124" name="Constant_32756" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="313748588" size="8" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="125" name="Constant_32757" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="126" name="Gather_32758" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64" names="81" />
+			</output>
+		</layer>
+		<layer id="127" name="Constant_32764" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="294067292" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="128" name="Constant_32765" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="129" name="Gather_32766" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
 				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64" names="83" />
+			</output>
+		</layer>
+		<layer id="130" name="__module.model.model.decoder/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" names="85" />
+			</output>
+		</layer>
+		<layer id="131" name="__module.model.model.decoder/aten::add/Multiply_2" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="294067292" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="132" name="__module.model.model.decoder/aten::add/Add_2" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" names="86,88" />
+			</output>
+		</layer>
+		<layer id="133" name="__module.model.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="313748596" size="4" />
+			<output>
+				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="131" name="Constant_31923" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="134" name="__module.model.model.decoder/aten::arange/Range" type="Range" version="opset4">
+			<data output_type="f32" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="132" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="135" name="__module.model.model.decoder/aten::arange/ConvertLike" type="Convert" version="opset1">
+			<data destination_type="i64" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="125,tensor.5">
+				<port id="1" precision="I64" names="92">
 					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="133" name="Constant_32240" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="136" name="Constant_24926" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="313748600" size="16" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>4</dim>
+				<port id="0" precision="I64" names="93">
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="134" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="137" name="__module.model.model.decoder/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="I64">
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
 				<port id="1" precision="I64">
-					<dim>4</dim>
+					<dim>2</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="127">
-					<dim>-1</dim>
+				<port id="2" precision="I64" names="94">
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="135" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="138" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I32">
-					<dim>4</dim>
+				<port id="2" precision="BOOL" names="95">
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="136" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+		<layer id="139" name="__module.model.model.decoder/aten::mul_/ConvertLike" type="Convert" version="opset1">
+			<data destination_type="f32" />
 			<input>
-				<port id="0" precision="FP32">
+				<port id="0" precision="BOOL">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.0.decoder.value">
+				<port id="1" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="137" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="false" />
+		<layer id="140" name="Multiply_31190" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="140,attn_output.1">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="138" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="139" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+		<layer id="141" name="ShapeOf_31191" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="141,attn_output.3">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
+				<port id="1" precision="I64">
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="140" name="Constant_32241" type="Const" version="opset1">
-			<data element_type="i64" shape="3" offset="150318226" size="24" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="142" name="Constant_32769" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
 			<output>
 				<port id="0" precision="I64">
-					<dim>3</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="141" name="__module.model.model.decoder.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="143" name="Reshape_32770" type="Reshape" version="opset1">
+			<data special_zero="false" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
-				</port>
+				<port id="0" precision="I64" />
 				<port id="1" precision="I64">
-					<dim>3</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="143">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="2" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="142" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="150318250" size="3276800" />
+		<layer id="144" name="Constant_24912" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.self_attn.out_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="143" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="145" name="Unsqueeze_24913" type="Unsqueeze" version="opset1">
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I32" />
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="2" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="144" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="146" name="__module.model.model.decoder/prim::ListConstruct_1" type="Concat" version="opset1">
+			<data axis="0" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I64">
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="145" name="Constant_31924_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="153595050" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="2" precision="I64">
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="146" name="Constant_31924" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="147" name="Maximum_31192" type="Maximum" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="2" precision="I64">
+					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="147" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="148" name="__module.model.model.decoder/aten::mul_/Multiply" type="Broadcast" version="opset3">
+			<data mode="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I64">
+					<dim>2</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="146,148,input.7">
+				<port id="2" precision="FP32" names="91,causal_mask.1">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="148" name="__module.model.model.decoder.layers.0/aten::add/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="149" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
+				<port id="1" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="152,residual.3">
+				<port id="2" precision="FP32" names="97">
+					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="149" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="150" name="46" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="294067292" size="8" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
+				<port id="0" precision="I64" names="46" />
 			</output>
 		</layer>
-		<layer id="150" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="151" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_2" type="Unsqueeze" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
+					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
+				<port id="1" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="100,98,99">
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="151" name="Constant_31925_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="153597610" size="2560" />
+		<layer id="152" name="Constant_30625" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="153" name="Constant_30627" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
 			<output>
-				<port id="0" precision="FP16">
+				<port id="0" precision="I64">
 					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="154" name="Constant_30629" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
+			<output>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="152" name="Constant_31925" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="155" name="__module.model.model.decoder/prim::ListConstruct_2" type="Concat" version="opset1">
+			<data axis="0" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="2" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="3" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="153" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="156" name="__module.model.model.decoder/aten::expand/Broadcast" type="Broadcast" version="opset3">
+			<data mode="bidirectional" />
 			<input>
 				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="102,148,149,150,264,265,266,attention_mask">
 					<dim>-1</dim>
+					<dim>1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="157" name="Constant_25209" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="154" name="Constant_31926_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="153600170" size="2560" />
+		<layer id="158" name="Constant_32777" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="155" name="Constant_31926" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="159" name="Reshape_32778" type="Reshape" version="opset1">
+			<data special_zero="false" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="2" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="156" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+		<layer id="160" name="Add_32781" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
+				<port id="0" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="156,hidden_states.5">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="2" precision="I64" names="147,263">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="157" name="Constant_31825_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="153602730" size="3276800" />
+		<layer id="161" name="Constant_25212" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="294067292" size="8" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="158" name="Constant_31825" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="162" name="Constant_25207" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="313748616" size="8" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="159" name="Multiply_31809" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="163" name="__module.model.model.decoder.layers.0.self_attn/aten::slice/Slice_3" type="Slice" version="opset8">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32">
+					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="160" name="Constant_31927_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="156879530" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
+				<port id="1" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="2" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="161" name="Constant_31927" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
+				<port id="3" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="4" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="5" precision="FP32" names="151,267">
+					<dim>-1</dim>
 					<dim>1</dim>
-					<dim>1280</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="162" name="__module.model.model.decoder.layers.0.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="164" name="__module.model.model.decoder.layers.0.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
 					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="166,tensor.7">
+				<port id="4" precision="FP32" names="152,attn_output.1">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="163" name="Constant_32242" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="165" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
-				<port id="0" precision="I64">
+				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="164" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="166" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="I64">
+				<port id="1" precision="I32">
 					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="168">
+				<port id="2" precision="FP32" names="153,attn_output.3">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -2373,15 +2235,16 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="165" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="167" name="Constant_32952" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="313748624" size="24" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="I64">
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="166" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+		<layer id="168" name="__module.model.model.decoder.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2389,195 +2252,210 @@
 					<dim>20</dim>
 					<dim>64</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="1" precision="I64">
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="169">
+				<port id="2" precision="FP32" names="155">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="167" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="156882090" size="3276800" />
+		<layer id="169" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="313748648" size="6553600" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.self_attn.out_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="168" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="170" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
 					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="171" name="Constant_32327" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="320302248" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="169" name="__module.model.model.decoder.layers.0.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="172" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1280</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="172,tensor.9">
+				<port id="2" precision="FP32" names="158,160,input.3">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="170" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="173" name="__module.model.model.decoder.layers.0/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>4</dim>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="174">
+				<port id="2" precision="FP32" names="164,residual.3">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="171" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="174" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
 				<port id="0" precision="I32">
-					<dim>4</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="172" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+		<layer id="175" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>64</dim>
+					<dim>1280</dim>
 				</port>
 				<port id="1" precision="I32">
-					<dim>4</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.0.encoder.key">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="173" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="176" name="Constant_32328" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="320307368" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="177" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
+					<dim>1280</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>64</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="185,input.9">
-					<dim>-1</dim>
-					<dim>20</dim>
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="178" name="Constant_32329" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="320312488" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="174" name="__module.model.model.decoder.layers.0.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
-			<data axis="-1" />
+		<layer id="179" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="186,input.11">
-					<dim>-1</dim>
-					<dim>20</dim>
+				<port id="2" precision="FP32" names="168,hidden_states.5">
 					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="175" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="160158890" size="3276800" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight">
-					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="176" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="180" name="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="320317608" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="177" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="181" name="__module.model.model.decoder.layers.0.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1280</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1280</dim>
@@ -2592,37 +2470,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="178" name="Constant_31928_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="163435690" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="179" name="Constant_31928" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="182" name="Constant_32330" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="326871208" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="180" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+		<layer id="183" name="__module.model.model.decoder.layers.0.encoder_attn.q_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2637,15 +2495,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="179,tensor.11">
+				<port id="2" precision="FP32" names="177,tensor.7">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="181" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="184" name="Constant_32953" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="185" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2657,7 +2523,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="181">
+				<port id="2" precision="FP32" names="179">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -2665,15 +2531,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="182" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="186" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="183" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+		<layer id="187" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2686,7 +2552,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.0.encoder.value">
+				<port id="2" precision="FP32" names="180">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -2694,16 +2560,22 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="184" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="false" />
+		<layer id="188" name="__module.model.model.decoder.layers.0.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -2711,7 +2583,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="188,attn_output.5">
+				<port id="3" precision="FP32" names="195,attn_output.5">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -2719,15 +2591,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="185" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="189" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="186" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+		<layer id="190" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2740,7 +2612,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="189,attn_output.7">
+				<port id="2" precision="FP32" names="196,attn_output.7">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -2748,18 +2620,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="187" name="Constant_32243" type="Const" version="opset1">
-			<data element_type="i64" shape="3" offset="163438250" size="24" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="191" name="Constant_32956" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="313748624" size="24" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="188" name="__module.model.model.decoder.layers.0.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+		<layer id="192" name="__module.model.model.decoder.layers.0.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2773,41 +2642,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="191">
+				<port id="2" precision="FP32" names="198">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="189" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="163438274" size="3276800" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="190" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="193" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="326876328" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="191" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="194" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2828,37 +2679,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="192" name="Constant_31929_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="166715074" size="2560" />
+		<layer id="195" name="Constant_32332" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="333429928" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="193" name="Constant_31929" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="194" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+		<layer id="196" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2873,14 +2704,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="194,196,input.13">
+				<port id="2" precision="FP32" names="201,input.5">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="195" name="__module.model.model.decoder.layers.0/aten::add/Add_1" type="Add" version="opset1">
+		<layer id="197" name="__module.model.model.decoder.layers.0/aten::add/Add_1" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2895,22 +2726,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="200,residual.5">
+				<port id="2" precision="FP32" names="203,residual.5">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="196" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="198" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="197" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+		<layer id="199" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
 			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2930,37 +2761,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="198" name="Constant_31930_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="166717634" size="2560" />
+		<layer id="200" name="Constant_32333" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="333435048" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="199" name="Constant_31930" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="200" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+		<layer id="201" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2982,30 +2793,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="201" name="Constant_31931_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="166720194" size="2560" />
+		<layer id="202" name="Constant_32334" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="333440168" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="202" name="Constant_31931" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
@@ -3027,41 +2818,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="204">
+				<port id="2" precision="FP32" names="207">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="204" name="self.model.model.decoder.layers.0.fc1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="5120, 1280" offset="166722754" size="13107200" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.fc1.weight">
-					<dim>5120</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="205" name="self.model.model.decoder.layers.0.fc1.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>5120</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="204" name="self.model.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="5120, 1280" offset="333445288" size="26214400" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.fc1.weight">
 					<dim>5120</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="206" name="__module.model.model.decoder.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="205" name="__module.model.model.decoder.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3082,37 +2855,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="207" name="Constant_31932_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 5120" offset="179829954" size="10240" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>5120</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="208" name="Constant_31932" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>5120</dim>
-				</port>
-			</input>
+		<layer id="206" name="Constant_32335" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 5120" offset="359659688" size="20480" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="209" name="__module.model.model.decoder.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
+		<layer id="207" name="__module.model.model.decoder.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3127,14 +2880,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="207">
+				<port id="2" precision="FP32" names="210">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="210" name="__module.model.model.decoder.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+		<layer id="208" name="__module.model.model.decoder.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
 			<data approximation_mode="ERF" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3144,41 +2897,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="208,input.15">
+				<port id="1" precision="FP32" names="211,input.7">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="211" name="self.model.model.decoder.layers.0.fc2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 5120" offset="179840194" size="13107200" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.0.fc2.weight">
-					<dim>1280</dim>
-					<dim>5120</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="212" name="self.model.model.decoder.layers.0.fc2.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>5120</dim>
-				</port>
-			</input>
+		<layer id="209" name="self.model.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 5120" offset="359680168" size="26214400" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.0.fc2.weight">
 					<dim>1280</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="213" name="__module.model.model.decoder.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="210" name="__module.model.model.decoder.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3199,37 +2934,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="214" name="Constant_31933_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="192947394" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="215" name="Constant_31933" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="211" name="Constant_32336" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="385894568" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="216" name="__module.model.model.decoder.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
+		<layer id="212" name="__module.model.model.decoder.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3244,14 +2959,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="212,input.17">
+				<port id="2" precision="FP32" names="215,input.9">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="217" name="__module.model.model.decoder.layers.0/aten::add/Add_2" type="Add" version="opset1">
+		<layer id="213" name="__module.model.model.decoder.layers.0/aten::add/Add_2" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3266,22 +2981,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="214,216,residual.7">
+				<port id="2" precision="FP32" names="217,219,residual.7">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="218" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="214" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="219" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+		<layer id="215" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
 			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3301,37 +3016,49 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="220" name="Constant_31934_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="192949954" size="2560" />
+		<layer id="216" name="Constant_32337" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="385899688" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="221" name="Constant_31934" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="217" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="218" name="Constant_32338" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="385904808" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="222" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+		<layer id="219" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3346,44 +3073,54 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="232,hidden_states.11">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="223" name="Constant_31935_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="192952514" size="2560" />
+		<layer id="220" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="385909928" size="6553600" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.self_attn.v_proj.weight">
+					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="224" name="Constant_31935" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="221" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="222" name="Constant_32339" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="392463528" size="5120" />
+			<output>
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="225" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+		<layer id="223" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3398,167 +3135,206 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="231,hidden_states.11">
+				<port id="2" precision="FP32" names="254,tensor.17">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="226" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="192955074" size="3276800" />
+		<layer id="224" name="Constant_32957" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.self_attn.v_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="0" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="227" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="225" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="2" precision="FP32" names="256">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="228" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="226" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="227" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>20</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="257">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="228" name="__module.model.model.decoder.layers.1.self_attn/aten::cat/Concat" type="Concat" version="opset1">
+			<data axis="-2" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1280</dim>
-					<dim>1280</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="present.1.decoder.value">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>1280</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="229" name="Constant_31937_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="196231874" size="2560" />
+		<layer id="230" name="Constant_35065" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="26224688" size="4" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="231" name="Constant_35058" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224700" size="8" />
+			<output>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="230" name="Constant_31937" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+		<layer id="232" name="Constant_35060" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224692" size="8" />
+			<output>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="233" name="Constant_35062" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26224708" size="8" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="0" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="231" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+		<layer id="234" name="Concat_35063" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="2" precision="I64">
 					<dim>1</dim>
+				</port>
+				<port id="3" precision="I64">
 					<dim>1</dim>
-					<dim>1280</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="254,tensor.17">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
+				<port id="4" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="232" name="Constant_32244" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64">
+		<layer id="235" name="Broadcast_35066" type="Broadcast" version="opset3">
+			<data mode="numpy" />
+			<input>
+				<port id="0" precision="FP32" />
+				<port id="1" precision="I64">
 					<dim>4</dim>
 				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="233" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="236" name="ReadValue_34629" type="ReadValue" version="opset6">
+			<data variable_id="past_key_values.1.decoder.keypresent.1.decoder.key" variable_type="f32" variable_shape="?,20,?,64" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1280</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>4</dim>
+					<dim>20</dim>
+					<dim>0</dim>
+					<dim>64</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="256">
-					<dim>-1</dim>
+				<port id="1" precision="FP32" names="past_key_values.1.decoder.key">
 					<dim>-1</dim>
 					<dim>20</dim>
+					<dim>-1</dim>
 					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="234" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="237" name="Constant_34238" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26224692" size="8" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>4</dim>
-				</port>
+				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="235" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+		<layer id="238" name="Gather_34239" type="Gather" version="opset8">
+			<data batch_dims="0" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
+					<dim>-1</dim>
 					<dim>64</dim>
 				</port>
 				<port id="1" precision="I32">
-					<dim>4</dim>
+					<dim>-1</dim>
 				</port>
+				<port id="2" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.1.decoder.value">
+				<port id="3" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -3566,34 +3342,16 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="237" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="196234434" size="3276800" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.self_attn.k_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="238" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="239" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="392468648" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.self_attn.k_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="239" name="__module.model.model.decoder.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="240" name="__module.model.model.decoder.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3614,18 +3372,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="240" name="Constant_32245" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="241" name="Constant_32958" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="241" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+		<layer id="242" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3646,15 +3401,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="242" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="243" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="243" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+		<layer id="244" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3667,7 +3422,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="present.1.decoder.key">
+				<port id="2" precision="FP32" names="250">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -3675,34 +3430,41 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="249" name="Constant_31828_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="199511234" size="3276800" />
+		<layer id="245" name="__module.model.model.decoder.layers.1.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
+			<data axis="-2" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
+				<port id="2" precision="FP32" names="key_states">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="250" name="Constant_31828" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="249" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="399022248" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.self_attn.q_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="251" name="Multiply_31813" type="MatMul" version="opset1">
+		<layer id="250" name="__module.model.model.decoder.layers.1.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3723,37 +3485,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="252" name="Constant_31936_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="202788034" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="253" name="Constant_31936" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="251" name="Constant_32340" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="405575848" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="254" name="__module.model.model.decoder.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+		<layer id="252" name="__module.model.model.decoder.layers.1.self_attn.q_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3775,18 +3517,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="255" name="Constant_32246" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="253" name="Constant_32959" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="256" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+		<layer id="254" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3807,15 +3546,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="257" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="255" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="258" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+		<layer id="256" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3836,8 +3575,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="259" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="257" name="__module.model.model.decoder.layers.1.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3851,26 +3590,13 @@
 					<dim>-1</dim>
 					<dim>64</dim>
 				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="260,attn_weights">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="260" name="__module.model.model.decoder.layers.1.self_attn/aten::add/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>64</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="3" precision="FP32">
 					<dim>-1</dim>
 					<dim>1</dim>
 					<dim>-1</dim>
@@ -3878,51 +3604,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="266,input.19">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="261" name="__module.model.model.decoder.layers.1.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
-			<data axis="-1" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="267,input.21">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="262" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="false" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>64</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="269,attn_output.9">
+				<port id="4" precision="FP32" names="268,attn_output.9">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -3930,15 +3612,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="263" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="258" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="264" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+		<layer id="259" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3951,7 +3633,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="270,attn_output.11">
+				<port id="2" precision="FP32" names="269,attn_output.11">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -3959,18 +3641,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="265" name="Constant_32247" type="Const" version="opset1">
-			<data element_type="i64" shape="3" offset="150318226" size="24" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="260" name="Constant_32960" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="313748624" size="24" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="266" name="__module.model.model.decoder.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+		<layer id="261" name="__module.model.model.decoder.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3984,41 +3663,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="272">
+				<port id="2" precision="FP32" names="271">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="267" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="202790594" size="3276800" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.self_attn.out_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="268" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="262" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="405580968" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.self_attn.out_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="269" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="263" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4039,37 +3700,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="270" name="Constant_31938_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="206067394" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="271" name="Constant_31938" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="264" name="Constant_32341" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="412134568" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="272" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+		<layer id="265" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4084,14 +3725,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="275,277,input.23">
+				<port id="2" precision="FP32" names="274,276,input.11">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="273" name="__module.model.model.decoder.layers.1/aten::add/Add" type="Add" version="opset1">
+		<layer id="266" name="__module.model.model.decoder.layers.1/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4106,22 +3747,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="281,residual.9">
+				<port id="2" precision="FP32" names="280,residual.9">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="274" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="267" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="275" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+		<layer id="268" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
 			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4141,37 +3782,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="276" name="Constant_31939_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="206069954" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="277" name="Constant_31939" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="269" name="Constant_32342" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="412139688" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="278" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+		<layer id="270" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4193,37 +3814,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="279" name="Constant_31940_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="206072514" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="280" name="Constant_31940" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="271" name="Constant_32343" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="412144808" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="281" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+		<layer id="272" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4238,41 +3839,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="285,hidden_states.15">
+				<port id="2" precision="FP32" names="284,hidden_states.15">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="282" name="Constant_31831_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="206075074" size="3276800" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="283" name="Constant_31831" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="273" name="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="412149928" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="284" name="Multiply_31817" type="MatMul" version="opset1">
+		<layer id="274" name="__module.model.model.decoder.layers.1.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4293,37 +3876,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="285" name="Constant_31941_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="209351874" size="2560" />
+		<layer id="275" name="Constant_32344" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="418703528" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="286" name="Constant_31941" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="287" name="__module.model.model.decoder.layers.1.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+		<layer id="276" name="__module.model.model.decoder.layers.1.encoder_attn.q_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4338,25 +3901,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="295,tensor.19">
+				<port id="2" precision="FP32" names="293,tensor.19">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="288" name="Constant_32248" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="143762004" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="277" name="Constant_32961" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="6553600" size="32" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="289" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+		<layer id="278" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4369,7 +3929,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="297">
+				<port id="2" precision="FP32" names="295">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -4377,15 +3937,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="290" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="279" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="291" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
+		<layer id="280" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -4398,7 +3958,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="298">
+				<port id="2" precision="FP32" names="296">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -4406,8 +3966,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="292" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="true" />
+		<layer id="281" name="__module.model.model.decoder.layers.1.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -4421,45 +3981,7 @@
 					<dim>-1</dim>
 					<dim>64</dim>
 				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="314,input.25">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="293" name="__module.model.model.decoder.layers.1.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
-			<data axis="-1" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="315,input.27">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="294" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
-			<data transpose_a="false" transpose_b="false" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>20</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -4467,7 +3989,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="317,attn_output.13">
+				<port id="3" precision="FP32" names="311,attn_output.13">
 					<dim>-1</dim>
 					<dim>20</dim>
 					<dim>-1</dim>
@@ -4475,15 +3997,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="295" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
-			<data element_type="i32" shape="4" offset="3279392" size="16" />
+		<layer id="282" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="6553632" size="16" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="296" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+		<layer id="283" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -4496,7 +4018,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="318,attn_output">
+				<port id="2" precision="FP32" names="312,attn_output">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>20</dim>
@@ -4504,18 +4026,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="297" name="Constant_32249" type="Const" version="opset1">
-			<data element_type="i64" shape="3" offset="163438250" size="24" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="284" name="Constant_32964" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="313748624" size="24" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="298" name="__module.model.model.decoder.layers.1.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+		<layer id="285" name="__module.model.model.decoder.layers.1.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4529,41 +4048,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="320">
+				<port id="2" precision="FP32" names="314">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="299" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 1280" offset="209354434" size="3276800" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="300" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="286" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 1280" offset="418708648" size="6553600" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight">
 					<dim>1280</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="301" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="287" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4584,37 +4085,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="302" name="Constant_31942_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="212631234" size="2560" />
+		<layer id="288" name="Constant_32346" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="425262248" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="303" name="Constant_31942" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="304" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+		<layer id="289" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4629,14 +4110,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="323,325,input.29">
+				<port id="2" precision="FP32" names="317,input.13">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="305" name="__module.model.model.decoder.layers.1/aten::add/Add_1" type="Add" version="opset1">
+		<layer id="290" name="__module.model.model.decoder.layers.1/aten::add/Add_1" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4651,22 +4132,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="329,residual">
+				<port id="2" precision="FP32" names="319,residual">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="306" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="291" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="307" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+		<layer id="292" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
 			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4686,37 +4167,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="308" name="Constant_31943_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="212633794" size="2560" />
+		<layer id="293" name="Constant_32347" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="425267368" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="309" name="Constant_31943" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="310" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+		<layer id="294" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4738,37 +4199,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="311" name="Constant_31944_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="212636354" size="2560" />
+		<layer id="295" name="Constant_32348" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="425272488" size="5120" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="312" name="Constant_31944" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="313" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+		<layer id="296" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4783,41 +4224,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="333">
+				<port id="2" precision="FP32" names="323">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="314" name="self.model.model.decoder.layers.1.fc1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="5120, 1280" offset="212638914" size="13107200" />
+		<layer id="297" name="self.model.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="5120, 1280" offset="425277608" size="26214400" />
 			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.fc1.weight">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.fc1.weight">
 					<dim>5120</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="315" name="self.model.model.decoder.layers.1.fc1.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>5120</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>5120</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="316" name="__module.model.model.decoder.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="298" name="__module.model.model.decoder.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4838,37 +4261,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="317" name="Constant_31945_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 5120" offset="225746114" size="10240" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>5120</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="318" name="Constant_31945" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>5120</dim>
-				</port>
-			</input>
+		<layer id="299" name="Constant_32349" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 5120" offset="451492008" size="20480" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="319" name="__module.model.model.decoder.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
+		<layer id="300" name="__module.model.model.decoder.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4883,14 +4286,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="336">
+				<port id="2" precision="FP32" names="326">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="320" name="__module.model.model.decoder.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+		<layer id="301" name="__module.model.model.decoder.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
 			<data approximation_mode="ERF" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4900,41 +4303,23 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="337,input.31">
+				<port id="1" precision="FP32" names="327,input.15">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="321" name="self.model.model.decoder.layers.1.fc2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1280, 5120" offset="225756354" size="13107200" />
-			<output>
-				<port id="0" precision="FP16" names="self.model.model.decoder.layers.1.fc2.weight">
-					<dim>1280</dim>
-					<dim>5120</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="322" name="self.model.model.decoder.layers.1.fc2.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1280</dim>
-					<dim>5120</dim>
-				</port>
-			</input>
+		<layer id="302" name="self.model.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="1280, 5120" offset="451512488" size="26214400" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32" names="self.model.model.decoder.layers.1.fc2.weight">
 					<dim>1280</dim>
 					<dim>5120</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="323" name="__module.model.model.decoder.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="303" name="__module.model.model.decoder.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4955,37 +4340,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="324" name="Constant_31946_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="238863554" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="325" name="Constant_31946" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="304" name="Constant_32350" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="477726888" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="326" name="__module.model.model.decoder.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
+		<layer id="305" name="__module.model.model.decoder.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5000,14 +4365,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="341,input">
+				<port id="2" precision="FP32" names="331,input">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="327" name="__module.model.model.decoder.layers.1/aten::add/Add_2" type="Add" version="opset1">
+		<layer id="306" name="__module.model.model.decoder.layers.1/aten::add/Add_2" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5022,22 +4387,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="343,345">
+				<port id="2" precision="FP32" names="333,335">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="328" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="140477520" size="4" />
+		<layer id="307" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="294067300" size="4" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="329" name="__module.model.model.decoder.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+		<layer id="308" name="__module.model.model.decoder.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
 			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5057,37 +4422,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="330" name="Constant_31947_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="238866114" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="331" name="Constant_31947" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="309" name="Constant_32351" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="477732008" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="332" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+		<layer id="310" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5109,37 +4454,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="333" name="Constant_31948_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1280" offset="238868674" size="2560" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="334" name="Constant_31948" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1280</dim>
-				</port>
-			</input>
+		<layer id="311" name="Constant_32352" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1280" offset="477737128" size="5120" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="335" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+		<layer id="312" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5154,14 +4479,14 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="353,355,365">
+				<port id="2" precision="FP32" names="341,343,349">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1280</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="336" name="__module.model.proj_out/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="313" name="__module.model.proj_out/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5182,16 +4507,27 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="337" name="Result_26725" type="Result" version="opset1">
+		<layer id="248" name="Assign_34626" type="Assign" version="opset6">
+			<data variable_id="past_key_values.0.decoder.keypresent.0.decoder.key" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>51865</dim>
+					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="248" name="Result_26731" type="Result" version="opset1">
+		<layer id="247" name="Assign_34628" type="Assign" version="opset6">
+			<data variable_id="past_key_values.0.decoder.valuepresent.0.decoder.value" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5200,8 +4536,17 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="247" name="Result_26730" type="Result" version="opset1">
+		<layer id="246" name="Assign_34630" type="Assign" version="opset6">
+			<data variable_id="past_key_values.1.decoder.keypresent.1.decoder.key" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5210,8 +4555,17 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="246" name="Result_26729" type="Result" version="opset1">
+		<layer id="229" name="Assign_34632" type="Assign" version="opset6">
+			<data variable_id="past_key_values.1.decoder.valuepresent.1.decoder.value" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5220,8 +4574,17 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="245" name="Result_26728" type="Result" version="opset1">
+		<layer id="39" name="Assign_35460" type="Assign" version="opset6">
+			<data variable_id="193" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5230,8 +4593,17 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="244" name="Result_26735" type="Result" version="opset1">
+		<layer id="29" name="Assign_35462" type="Assign" version="opset6">
+			<data variable_id="302" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5240,8 +4612,17 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="236" name="Result_26734" type="Result" version="opset1">
+		<layer id="21" name="Assign_35464" type="Assign" version="opset6">
+			<data variable_id="309" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5250,8 +4631,17 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="26" name="Result_26733" type="Result" version="opset1">
+		<layer id="11" name="Assign_35466" type="Assign" version="opset6">
+			<data variable_id="186" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5260,402 +4650,389 @@
 					<dim>64</dim>
 				</port>
 			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>20</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
 		</layer>
-		<layer id="19" name="Result_26732" type="Result" version="opset1">
+		<layer id="314" name="Result_26174" type="Result" version="opset1" output_names="logits">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>20</dim>
 					<dim>-1</dim>
-					<dim>64</dim>
+					<dim>51865</dim>
 				</port>
 			</input>
 		</layer>
 	</layers>
 	<edges>
-		<edge from-layer="0" from-port="0" to-layer="4" to-port="0" />
-		<edge from-layer="0" from-port="0" to-layer="22" to-port="0" />
-		<edge from-layer="0" from-port="0" to-layer="169" to-port="0" />
-		<edge from-layer="0" from-port="0" to-layer="177" to-port="0" />
-		<edge from-layer="1" from-port="0" to-layer="30" to-port="0" />
-		<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
-		<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
-		<edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
-		<edge from-layer="4" from-port="2" to-layer="7" to-port="0" />
-		<edge from-layer="5" from-port="0" to-layer="6" to-port="0" />
-		<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
-		<edge from-layer="7" from-port="2" to-layer="16" to-port="0" />
-		<edge from-layer="8" from-port="1" to-layer="11" to-port="0" />
-		<edge from-layer="8" from-port="1" to-layer="39" to-port="0" />
-		<edge from-layer="9" from-port="0" to-layer="11" to-port="1" />
-		<edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
-		<edge from-layer="11" from-port="3" to-layer="15" to-port="0" />
-		<edge from-layer="11" from-port="3" to-layer="115" to-port="0" />
-		<edge from-layer="12" from-port="0" to-layer="15" to-port="1" />
-		<edge from-layer="13" from-port="0" to-layer="15" to-port="2" />
-		<edge from-layer="14" from-port="0" to-layer="15" to-port="3" />
-		<edge from-layer="15" from-port="4" to-layer="170" to-port="1" />
-		<edge from-layer="15" from-port="4" to-layer="181" to-port="1" />
-		<edge from-layer="15" from-port="4" to-layer="23" to-port="1" />
-		<edge from-layer="15" from-port="4" to-layer="16" to-port="1" />
-		<edge from-layer="16" from-port="2" to-layer="18" to-port="0" />
-		<edge from-layer="17" from-port="0" to-layer="18" to-port="1" />
-		<edge from-layer="18" from-port="2" to-layer="19" to-port="0" />
-		<edge from-layer="18" from-port="2" to-layer="294" to-port="1" />
-		<edge from-layer="20" from-port="0" to-layer="21" to-port="0" />
-		<edge from-layer="21" from-port="1" to-layer="22" to-port="1" />
-		<edge from-layer="22" from-port="2" to-layer="23" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="238" to-port="1" />
+		<edge from-layer="0" from-port="0" to-layer="111" to-port="1" />
+		<edge from-layer="0" from-port="0" to-layer="95" to-port="1" />
+		<edge from-layer="0" from-port="0" to-layer="52" to-port="1" />
+		<edge from-layer="1" from-port="0" to-layer="137" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="61" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="5" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="31" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="23" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="62" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="55" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="41" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="1" />
+		<edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
+		<edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
+		<edge from-layer="7" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="8" from-port="0" to-layer="9" to-port="1" />
+		<edge from-layer="9" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="10" from-port="1" to-layer="188" to-port="1" />
+		<edge from-layer="10" from-port="1" to-layer="11" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
+		<edge from-layer="13" from-port="2" to-layer="15" to-port="0" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
+		<edge from-layer="15" from-port="2" to-layer="17" to-port="0" />
+		<edge from-layer="16" from-port="0" to-layer="17" to-port="1" />
+		<edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="20" to-port="0" />
+		<edge from-layer="20" from-port="1" to-layer="21" to-port="0" />
+		<edge from-layer="20" from-port="1" to-layer="281" to-port="2" />
+		<edge from-layer="22" from-port="0" to-layer="23" to-port="1" />
 		<edge from-layer="23" from-port="2" to-layer="25" to-port="0" />
 		<edge from-layer="24" from-port="0" to-layer="25" to-port="1" />
-		<edge from-layer="25" from-port="2" to-layer="292" to-port="1" />
-		<edge from-layer="25" from-port="2" to-layer="26" to-port="0" />
-		<edge from-layer="27" from-port="0" to-layer="28" to-port="0" />
-		<edge from-layer="28" from-port="1" to-layer="336" to-port="1" />
-		<edge from-layer="28" from-port="1" to-layer="33" to-port="0" />
-		<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
-		<edge from-layer="30" from-port="2" to-layer="31" to-port="0" />
-		<edge from-layer="31" from-port="1" to-layer="33" to-port="1" />
-		<edge from-layer="32" from-port="0" to-layer="33" to-port="2" />
-		<edge from-layer="33" from-port="3" to-layer="46" to-port="0" />
-		<edge from-layer="34" from-port="0" to-layer="35" to-port="0" />
-		<edge from-layer="35" from-port="1" to-layer="45" to-port="0" />
-		<edge from-layer="36" from-port="0" to-layer="41" to-port="0" />
-		<edge from-layer="36" from-port="0" to-layer="42" to-port="1" />
-		<edge from-layer="36" from-port="0" to-layer="109" to-port="1" />
-		<edge from-layer="37" from-port="0" to-layer="39" to-port="1" />
-		<edge from-layer="38" from-port="0" to-layer="39" to-port="2" />
-		<edge from-layer="39" from-port="3" to-layer="41" to-port="1" />
-		<edge from-layer="39" from-port="3" to-layer="78" to-port="0" />
-		<edge from-layer="39" from-port="3" to-layer="76" to-port="0" />
-		<edge from-layer="39" from-port="3" to-layer="91" to-port="0" />
-		<edge from-layer="40" from-port="0" to-layer="41" to-port="2" />
-		<edge from-layer="41" from-port="3" to-layer="42" to-port="0" />
-		<edge from-layer="41" from-port="3" to-layer="105" to-port="0" />
-		<edge from-layer="42" from-port="2" to-layer="43" to-port="0" />
-		<edge from-layer="43" from-port="1" to-layer="45" to-port="1" />
-		<edge from-layer="44" from-port="0" to-layer="45" to-port="2" />
-		<edge from-layer="45" from-port="3" to-layer="46" to-port="1" />
-		<edge from-layer="46" from-port="2" to-layer="48" to-port="0" />
-		<edge from-layer="46" from-port="2" to-layer="148" to-port="0" />
-		<edge from-layer="47" from-port="0" to-layer="48" to-port="1" />
-		<edge from-layer="48" from-port="2" to-layer="51" to-port="0" />
-		<edge from-layer="49" from-port="0" to-layer="50" to-port="0" />
-		<edge from-layer="50" from-port="1" to-layer="51" to-port="1" />
-		<edge from-layer="51" from-port="2" to-layer="54" to-port="0" />
-		<edge from-layer="52" from-port="0" to-layer="53" to-port="0" />
-		<edge from-layer="53" from-port="1" to-layer="54" to-port="1" />
-		<edge from-layer="54" from-port="2" to-layer="118" to-port="0" />
-		<edge from-layer="54" from-port="2" to-layer="67" to-port="0" />
-		<edge from-layer="54" from-port="2" to-layer="129" to-port="0" />
-		<edge from-layer="54" from-port="2" to-layer="57" to-port="0" />
-		<edge from-layer="55" from-port="0" to-layer="56" to-port="0" />
-		<edge from-layer="56" from-port="1" to-layer="57" to-port="1" />
-		<edge from-layer="57" from-port="2" to-layer="60" to-port="0" />
-		<edge from-layer="58" from-port="0" to-layer="59" to-port="0" />
-		<edge from-layer="59" from-port="1" to-layer="60" to-port="1" />
-		<edge from-layer="60" from-port="2" to-layer="62" to-port="0" />
-		<edge from-layer="61" from-port="0" to-layer="62" to-port="1" />
-		<edge from-layer="62" from-port="2" to-layer="64" to-port="0" />
-		<edge from-layer="63" from-port="0" to-layer="64" to-port="1" />
-		<edge from-layer="64" from-port="2" to-layer="72" to-port="0" />
-		<edge from-layer="65" from-port="0" to-layer="66" to-port="0" />
-		<edge from-layer="66" from-port="1" to-layer="67" to-port="1" />
-		<edge from-layer="67" from-port="2" to-layer="69" to-port="0" />
-		<edge from-layer="68" from-port="0" to-layer="69" to-port="1" />
-		<edge from-layer="69" from-port="2" to-layer="71" to-port="0" />
-		<edge from-layer="70" from-port="0" to-layer="71" to-port="1" />
-		<edge from-layer="71" from-port="2" to-layer="248" to-port="0" />
-		<edge from-layer="71" from-port="2" to-layer="72" to-port="1" />
-		<edge from-layer="72" from-port="2" to-layer="125" to-port="0" />
-		<edge from-layer="73" from-port="0" to-layer="88" to-port="0" />
-		<edge from-layer="73" from-port="0" to-layer="89" to-port="1" />
-		<edge from-layer="74" from-port="0" to-layer="82" to-port="0" />
+		<edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
+		<edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
+		<edge from-layer="27" from-port="2" to-layer="28" to-port="0" />
+		<edge from-layer="28" from-port="1" to-layer="281" to-port="1" />
+		<edge from-layer="28" from-port="1" to-layer="29" to-port="0" />
+		<edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
+		<edge from-layer="31" from-port="2" to-layer="33" to-port="0" />
+		<edge from-layer="32" from-port="0" to-layer="33" to-port="1" />
+		<edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
+		<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
+		<edge from-layer="35" from-port="2" to-layer="37" to-port="0" />
+		<edge from-layer="36" from-port="0" to-layer="37" to-port="1" />
+		<edge from-layer="37" from-port="2" to-layer="38" to-port="0" />
+		<edge from-layer="38" from-port="1" to-layer="188" to-port="2" />
+		<edge from-layer="38" from-port="1" to-layer="39" to-port="0" />
+		<edge from-layer="40" from-port="0" to-layer="49" to-port="0" />
+		<edge from-layer="41" from-port="1" to-layer="44" to-port="0" />
+		<edge from-layer="42" from-port="0" to-layer="44" to-port="1" />
+		<edge from-layer="43" from-port="0" to-layer="44" to-port="2" />
+		<edge from-layer="44" from-port="3" to-layer="234" to-port="0" />
+		<edge from-layer="44" from-port="3" to-layer="48" to-port="0" />
+		<edge from-layer="44" from-port="3" to-layer="91" to-port="0" />
+		<edge from-layer="44" from-port="3" to-layer="107" to-port="0" />
+		<edge from-layer="45" from-port="0" to-layer="48" to-port="1" />
+		<edge from-layer="46" from-port="0" to-layer="48" to-port="2" />
+		<edge from-layer="47" from-port="0" to-layer="48" to-port="3" />
+		<edge from-layer="48" from-port="4" to-layer="49" to-port="1" />
+		<edge from-layer="49" from-port="2" to-layer="50" to-port="0" />
+		<edge from-layer="50" from-port="1" to-layer="52" to-port="0" />
+		<edge from-layer="51" from-port="0" to-layer="52" to-port="2" />
+		<edge from-layer="52" from-port="3" to-layer="228" to-port="0" />
+		<edge from-layer="53" from-port="0" to-layer="313" to-port="1" />
+		<edge from-layer="53" from-port="0" to-layer="58" to-port="0" />
+		<edge from-layer="54" from-port="0" to-layer="55" to-port="1" />
+		<edge from-layer="55" from-port="2" to-layer="56" to-port="0" />
+		<edge from-layer="56" from-port="1" to-layer="58" to-port="1" />
+		<edge from-layer="57" from-port="0" to-layer="58" to-port="2" />
+		<edge from-layer="58" from-port="3" to-layer="72" to-port="0" />
+		<edge from-layer="59" from-port="0" to-layer="71" to-port="0" />
+		<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
+		<edge from-layer="60" from-port="0" to-layer="149" to-port="1" />
+		<edge from-layer="61" from-port="2" to-layer="68" to-port="0" />
+		<edge from-layer="62" from-port="1" to-layer="129" to-port="0" />
+		<edge from-layer="62" from-port="1" to-layer="65" to-port="0" />
+		<edge from-layer="63" from-port="0" to-layer="65" to-port="1" />
+		<edge from-layer="64" from-port="0" to-layer="65" to-port="2" />
+		<edge from-layer="65" from-port="3" to-layer="155" to-port="0" />
+		<edge from-layer="65" from-port="3" to-layer="67" to-port="0" />
+		<edge from-layer="66" from-port="0" to-layer="67" to-port="1" />
+		<edge from-layer="67" from-port="2" to-layer="68" to-port="1" />
+		<edge from-layer="68" from-port="2" to-layer="69" to-port="0" />
+		<edge from-layer="69" from-port="1" to-layer="71" to-port="1" />
+		<edge from-layer="70" from-port="0" to-layer="71" to-port="2" />
+		<edge from-layer="71" from-port="3" to-layer="72" to-port="1" />
+		<edge from-layer="72" from-port="2" to-layer="173" to-port="0" />
+		<edge from-layer="72" from-port="2" to-layer="74" to-port="0" />
+		<edge from-layer="73" from-port="0" to-layer="74" to-port="1" />
+		<edge from-layer="74" from-port="2" to-layer="76" to-port="0" />
 		<edge from-layer="75" from-port="0" to-layer="76" to-port="1" />
-		<edge from-layer="76" from-port="2" to-layer="81" to-port="0" />
+		<edge from-layer="76" from-port="2" to-layer="78" to-port="0" />
 		<edge from-layer="77" from-port="0" to-layer="78" to-port="1" />
-		<edge from-layer="78" from-port="2" to-layer="101" to-port="1" />
 		<edge from-layer="78" from-port="2" to-layer="80" to-port="0" />
+		<edge from-layer="78" from-port="2" to-layer="113" to-port="0" />
+		<edge from-layer="78" from-port="2" to-layer="97" to-port="0" />
 		<edge from-layer="79" from-port="0" to-layer="80" to-port="1" />
-		<edge from-layer="80" from-port="2" to-layer="81" to-port="1" />
-		<edge from-layer="81" from-port="2" to-layer="82" to-port="1" />
-		<edge from-layer="82" from-port="2" to-layer="83" to-port="0" />
-		<edge from-layer="82" from-port="2" to-layer="98" to-port="1" />
-		<edge from-layer="83" from-port="1" to-layer="86" to-port="0" />
-		<edge from-layer="84" from-port="0" to-layer="86" to-port="1" />
-		<edge from-layer="85" from-port="0" to-layer="86" to-port="2" />
-		<edge from-layer="86" from-port="3" to-layer="88" to-port="1" />
-		<edge from-layer="87" from-port="0" to-layer="94" to-port="1" />
-		<edge from-layer="87" from-port="0" to-layer="88" to-port="2" />
-		<edge from-layer="87" from-port="0" to-layer="93" to-port="2" />
-		<edge from-layer="88" from-port="3" to-layer="89" to-port="0" />
-		<edge from-layer="89" from-port="2" to-layer="95" to-port="0" />
-		<edge from-layer="90" from-port="0" to-layer="92" to-port="1" />
-		<edge from-layer="90" from-port="0" to-layer="93" to-port="0" />
-		<edge from-layer="91" from-port="1" to-layer="92" to-port="0" />
-		<edge from-layer="92" from-port="2" to-layer="93" to-port="1" />
-		<edge from-layer="93" from-port="3" to-layer="94" to-port="0" />
-		<edge from-layer="94" from-port="2" to-layer="95" to-port="1" />
-		<edge from-layer="95" from-port="2" to-layer="98" to-port="0" />
-		<edge from-layer="96" from-port="0" to-layer="97" to-port="0" />
-		<edge from-layer="97" from-port="1" to-layer="98" to-port="2" />
-		<edge from-layer="98" from-port="3" to-layer="108" to-port="0" />
-		<edge from-layer="99" from-port="0" to-layer="101" to-port="0" />
-		<edge from-layer="100" from-port="0" to-layer="101" to-port="2" />
-		<edge from-layer="101" from-port="3" to-layer="102" to-port="0" />
-		<edge from-layer="102" from-port="1" to-layer="103" to-port="0" />
-		<edge from-layer="103" from-port="1" to-layer="106" to-port="0" />
-		<edge from-layer="104" from-port="0" to-layer="105" to-port="1" />
-		<edge from-layer="105" from-port="2" to-layer="106" to-port="1" />
-		<edge from-layer="106" from-port="2" to-layer="107" to-port="0" />
-		<edge from-layer="107" from-port="1" to-layer="108" to-port="1" />
+		<edge from-layer="80" from-port="2" to-layer="82" to-port="0" />
+		<edge from-layer="81" from-port="0" to-layer="82" to-port="1" />
+		<edge from-layer="82" from-port="2" to-layer="84" to-port="0" />
+		<edge from-layer="83" from-port="0" to-layer="84" to-port="1" />
+		<edge from-layer="84" from-port="2" to-layer="86" to-port="0" />
+		<edge from-layer="85" from-port="0" to-layer="86" to-port="1" />
+		<edge from-layer="86" from-port="2" to-layer="164" to-port="0" />
+		<edge from-layer="87" from-port="0" to-layer="92" to-port="0" />
+		<edge from-layer="88" from-port="0" to-layer="91" to-port="1" />
+		<edge from-layer="89" from-port="0" to-layer="91" to-port="2" />
+		<edge from-layer="90" from-port="0" to-layer="91" to-port="3" />
+		<edge from-layer="91" from-port="4" to-layer="92" to-port="1" />
+		<edge from-layer="92" from-port="2" to-layer="93" to-port="0" />
+		<edge from-layer="93" from-port="1" to-layer="95" to-port="0" />
+		<edge from-layer="94" from-port="0" to-layer="95" to-port="2" />
+		<edge from-layer="95" from-port="3" to-layer="123" to-port="0" />
+		<edge from-layer="95" from-port="3" to-layer="102" to-port="0" />
+		<edge from-layer="96" from-port="0" to-layer="97" to-port="1" />
+		<edge from-layer="97" from-port="2" to-layer="99" to-port="0" />
+		<edge from-layer="98" from-port="0" to-layer="99" to-port="1" />
+		<edge from-layer="99" from-port="2" to-layer="101" to-port="0" />
+		<edge from-layer="100" from-port="0" to-layer="101" to-port="1" />
+		<edge from-layer="101" from-port="2" to-layer="102" to-port="1" />
+		<edge from-layer="102" from-port="2" to-layer="164" to-port="1" />
+		<edge from-layer="102" from-port="2" to-layer="248" to-port="0" />
+		<edge from-layer="103" from-port="0" to-layer="108" to-port="0" />
+		<edge from-layer="104" from-port="0" to-layer="107" to-port="1" />
+		<edge from-layer="105" from-port="0" to-layer="107" to-port="2" />
+		<edge from-layer="106" from-port="0" to-layer="107" to-port="3" />
+		<edge from-layer="107" from-port="4" to-layer="108" to-port="1" />
 		<edge from-layer="108" from-port="2" to-layer="109" to-port="0" />
-		<edge from-layer="109" from-port="2" to-layer="111" to-port="0" />
-		<edge from-layer="110" from-port="0" to-layer="111" to-port="1" />
-		<edge from-layer="111" from-port="2" to-layer="116" to-port="0" />
-		<edge from-layer="112" from-port="0" to-layer="115" to-port="1" />
-		<edge from-layer="113" from-port="0" to-layer="115" to-port="2" />
-		<edge from-layer="114" from-port="0" to-layer="115" to-port="3" />
-		<edge from-layer="115" from-port="4" to-layer="116" to-port="1" />
-		<edge from-layer="116" from-port="2" to-layer="124" to-port="0" />
-		<edge from-layer="117" from-port="0" to-layer="124" to-port="1" />
-		<edge from-layer="118" from-port="1" to-layer="121" to-port="0" />
-		<edge from-layer="119" from-port="0" to-layer="121" to-port="1" />
-		<edge from-layer="120" from-port="0" to-layer="121" to-port="2" />
-		<edge from-layer="121" from-port="3" to-layer="124" to-port="2" />
-		<edge from-layer="122" from-port="0" to-layer="124" to-port="3" />
-		<edge from-layer="123" from-port="0" to-layer="124" to-port="4" />
-		<edge from-layer="124" from-port="5" to-layer="260" to-port="1" />
-		<edge from-layer="124" from-port="5" to-layer="125" to-port="1" />
-		<edge from-layer="125" from-port="2" to-layer="126" to-port="0" />
-		<edge from-layer="126" from-port="1" to-layer="137" to-port="0" />
-		<edge from-layer="127" from-port="0" to-layer="128" to-port="0" />
-		<edge from-layer="128" from-port="1" to-layer="129" to-port="1" />
-		<edge from-layer="129" from-port="2" to-layer="132" to-port="0" />
-		<edge from-layer="130" from-port="0" to-layer="131" to-port="0" />
-		<edge from-layer="131" from-port="1" to-layer="132" to-port="1" />
-		<edge from-layer="132" from-port="2" to-layer="134" to-port="0" />
-		<edge from-layer="133" from-port="0" to-layer="134" to-port="1" />
-		<edge from-layer="134" from-port="2" to-layer="136" to-port="0" />
-		<edge from-layer="135" from-port="0" to-layer="136" to-port="1" />
-		<edge from-layer="136" from-port="2" to-layer="137" to-port="1" />
-		<edge from-layer="136" from-port="2" to-layer="247" to-port="0" />
-		<edge from-layer="137" from-port="2" to-layer="139" to-port="0" />
-		<edge from-layer="138" from-port="0" to-layer="139" to-port="1" />
-		<edge from-layer="139" from-port="2" to-layer="141" to-port="0" />
-		<edge from-layer="140" from-port="0" to-layer="141" to-port="1" />
-		<edge from-layer="141" from-port="2" to-layer="144" to-port="0" />
-		<edge from-layer="142" from-port="0" to-layer="143" to-port="0" />
-		<edge from-layer="143" from-port="1" to-layer="144" to-port="1" />
-		<edge from-layer="144" from-port="2" to-layer="147" to-port="0" />
-		<edge from-layer="145" from-port="0" to-layer="146" to-port="0" />
-		<edge from-layer="146" from-port="1" to-layer="147" to-port="1" />
+		<edge from-layer="109" from-port="1" to-layer="111" to-port="0" />
+		<edge from-layer="110" from-port="0" to-layer="111" to-port="2" />
+		<edge from-layer="111" from-port="3" to-layer="120" to-port="0" />
+		<edge from-layer="112" from-port="0" to-layer="113" to-port="1" />
+		<edge from-layer="113" from-port="2" to-layer="115" to-port="0" />
+		<edge from-layer="114" from-port="0" to-layer="115" to-port="1" />
+		<edge from-layer="115" from-port="2" to-layer="117" to-port="0" />
+		<edge from-layer="116" from-port="0" to-layer="117" to-port="1" />
+		<edge from-layer="117" from-port="2" to-layer="119" to-port="0" />
+		<edge from-layer="118" from-port="0" to-layer="119" to-port="1" />
+		<edge from-layer="119" from-port="2" to-layer="120" to-port="1" />
+		<edge from-layer="120" from-port="2" to-layer="164" to-port="2" />
+		<edge from-layer="120" from-port="2" to-layer="247" to-port="0" />
+		<edge from-layer="121" from-port="0" to-layer="140" to-port="0" />
+		<edge from-layer="122" from-port="0" to-layer="134" to-port="0" />
+		<edge from-layer="123" from-port="1" to-layer="126" to-port="0" />
+		<edge from-layer="124" from-port="0" to-layer="126" to-port="1" />
+		<edge from-layer="125" from-port="0" to-layer="126" to-port="2" />
+		<edge from-layer="126" from-port="3" to-layer="159" to-port="0" />
+		<edge from-layer="126" from-port="3" to-layer="130" to-port="0" />
+		<edge from-layer="127" from-port="0" to-layer="129" to-port="1" />
+		<edge from-layer="128" from-port="0" to-layer="129" to-port="2" />
+		<edge from-layer="129" from-port="3" to-layer="143" to-port="0" />
+		<edge from-layer="129" from-port="3" to-layer="130" to-port="1" />
+		<edge from-layer="130" from-port="2" to-layer="132" to-port="0" />
+		<edge from-layer="131" from-port="0" to-layer="132" to-port="1" />
+		<edge from-layer="132" from-port="2" to-layer="145" to-port="0" />
+		<edge from-layer="132" from-port="2" to-layer="134" to-port="1" />
+		<edge from-layer="133" from-port="0" to-layer="134" to-port="2" />
+		<edge from-layer="134" from-port="3" to-layer="135" to-port="0" />
+		<edge from-layer="135" from-port="1" to-layer="138" to-port="0" />
+		<edge from-layer="136" from-port="0" to-layer="137" to-port="1" />
+		<edge from-layer="137" from-port="2" to-layer="138" to-port="1" />
+		<edge from-layer="138" from-port="2" to-layer="139" to-port="0" />
+		<edge from-layer="139" from-port="1" to-layer="140" to-port="1" />
+		<edge from-layer="140" from-port="2" to-layer="141" to-port="0" />
+		<edge from-layer="140" from-port="2" to-layer="148" to-port="0" />
+		<edge from-layer="141" from-port="1" to-layer="147" to-port="0" />
+		<edge from-layer="142" from-port="0" to-layer="143" to-port="1" />
+		<edge from-layer="143" from-port="2" to-layer="146" to-port="0" />
+		<edge from-layer="143" from-port="2" to-layer="160" to-port="1" />
+		<edge from-layer="144" from-port="0" to-layer="145" to-port="1" />
+		<edge from-layer="145" from-port="2" to-layer="146" to-port="1" />
+		<edge from-layer="146" from-port="2" to-layer="147" to-port="1" />
 		<edge from-layer="147" from-port="2" to-layer="148" to-port="1" />
-		<edge from-layer="148" from-port="2" to-layer="195" to-port="0" />
-		<edge from-layer="148" from-port="2" to-layer="150" to-port="0" />
-		<edge from-layer="149" from-port="0" to-layer="150" to-port="1" />
-		<edge from-layer="150" from-port="2" to-layer="153" to-port="0" />
-		<edge from-layer="151" from-port="0" to-layer="152" to-port="0" />
-		<edge from-layer="152" from-port="1" to-layer="153" to-port="1" />
-		<edge from-layer="153" from-port="2" to-layer="156" to-port="0" />
-		<edge from-layer="154" from-port="0" to-layer="155" to-port="0" />
-		<edge from-layer="155" from-port="1" to-layer="156" to-port="1" />
-		<edge from-layer="156" from-port="2" to-layer="159" to-port="0" />
-		<edge from-layer="157" from-port="0" to-layer="158" to-port="0" />
-		<edge from-layer="158" from-port="1" to-layer="159" to-port="1" />
-		<edge from-layer="159" from-port="2" to-layer="162" to-port="0" />
-		<edge from-layer="160" from-port="0" to-layer="161" to-port="0" />
-		<edge from-layer="161" from-port="1" to-layer="162" to-port="1" />
-		<edge from-layer="162" from-port="2" to-layer="164" to-port="0" />
-		<edge from-layer="163" from-port="0" to-layer="164" to-port="1" />
-		<edge from-layer="164" from-port="2" to-layer="166" to-port="0" />
+		<edge from-layer="148" from-port="2" to-layer="149" to-port="0" />
+		<edge from-layer="149" from-port="2" to-layer="151" to-port="0" />
+		<edge from-layer="150" from-port="0" to-layer="151" to-port="1" />
+		<edge from-layer="151" from-port="2" to-layer="156" to-port="0" />
+		<edge from-layer="152" from-port="0" to-layer="155" to-port="1" />
+		<edge from-layer="153" from-port="0" to-layer="155" to-port="2" />
+		<edge from-layer="154" from-port="0" to-layer="155" to-port="3" />
+		<edge from-layer="155" from-port="4" to-layer="156" to-port="1" />
+		<edge from-layer="156" from-port="2" to-layer="163" to-port="0" />
+		<edge from-layer="157" from-port="0" to-layer="163" to-port="1" />
+		<edge from-layer="158" from-port="0" to-layer="159" to-port="1" />
+		<edge from-layer="159" from-port="2" to-layer="160" to-port="0" />
+		<edge from-layer="160" from-port="2" to-layer="163" to-port="2" />
+		<edge from-layer="161" from-port="0" to-layer="163" to-port="3" />
+		<edge from-layer="162" from-port="0" to-layer="163" to-port="4" />
+		<edge from-layer="163" from-port="5" to-layer="257" to-port="3" />
+		<edge from-layer="163" from-port="5" to-layer="164" to-port="3" />
+		<edge from-layer="164" from-port="4" to-layer="166" to-port="0" />
 		<edge from-layer="165" from-port="0" to-layer="166" to-port="1" />
-		<edge from-layer="166" from-port="2" to-layer="173" to-port="0" />
-		<edge from-layer="167" from-port="0" to-layer="168" to-port="0" />
-		<edge from-layer="168" from-port="1" to-layer="169" to-port="1" />
-		<edge from-layer="169" from-port="2" to-layer="170" to-port="0" />
+		<edge from-layer="166" from-port="2" to-layer="168" to-port="0" />
+		<edge from-layer="167" from-port="0" to-layer="168" to-port="1" />
+		<edge from-layer="168" from-port="2" to-layer="170" to-port="0" />
+		<edge from-layer="169" from-port="0" to-layer="170" to-port="1" />
 		<edge from-layer="170" from-port="2" to-layer="172" to-port="0" />
 		<edge from-layer="171" from-port="0" to-layer="172" to-port="1" />
 		<edge from-layer="172" from-port="2" to-layer="173" to-port="1" />
-		<edge from-layer="172" from-port="2" to-layer="246" to-port="0" />
-		<edge from-layer="173" from-port="2" to-layer="174" to-port="0" />
-		<edge from-layer="174" from-port="1" to-layer="184" to-port="0" />
-		<edge from-layer="175" from-port="0" to-layer="176" to-port="0" />
-		<edge from-layer="176" from-port="1" to-layer="177" to-port="1" />
-		<edge from-layer="177" from-port="2" to-layer="180" to-port="0" />
-		<edge from-layer="178" from-port="0" to-layer="179" to-port="0" />
-		<edge from-layer="179" from-port="1" to-layer="180" to-port="1" />
-		<edge from-layer="180" from-port="2" to-layer="181" to-port="0" />
+		<edge from-layer="173" from-port="2" to-layer="175" to-port="0" />
+		<edge from-layer="173" from-port="2" to-layer="197" to-port="0" />
+		<edge from-layer="174" from-port="0" to-layer="175" to-port="1" />
+		<edge from-layer="175" from-port="2" to-layer="177" to-port="0" />
+		<edge from-layer="176" from-port="0" to-layer="177" to-port="1" />
+		<edge from-layer="177" from-port="2" to-layer="179" to-port="0" />
+		<edge from-layer="178" from-port="0" to-layer="179" to-port="1" />
+		<edge from-layer="179" from-port="2" to-layer="181" to-port="0" />
+		<edge from-layer="180" from-port="0" to-layer="181" to-port="1" />
 		<edge from-layer="181" from-port="2" to-layer="183" to-port="0" />
 		<edge from-layer="182" from-port="0" to-layer="183" to-port="1" />
-		<edge from-layer="183" from-port="2" to-layer="245" to-port="0" />
-		<edge from-layer="183" from-port="2" to-layer="184" to-port="1" />
-		<edge from-layer="184" from-port="2" to-layer="186" to-port="0" />
-		<edge from-layer="185" from-port="0" to-layer="186" to-port="1" />
-		<edge from-layer="186" from-port="2" to-layer="188" to-port="0" />
-		<edge from-layer="187" from-port="0" to-layer="188" to-port="1" />
-		<edge from-layer="188" from-port="2" to-layer="191" to-port="0" />
-		<edge from-layer="189" from-port="0" to-layer="190" to-port="0" />
-		<edge from-layer="190" from-port="1" to-layer="191" to-port="1" />
-		<edge from-layer="191" from-port="2" to-layer="194" to-port="0" />
-		<edge from-layer="192" from-port="0" to-layer="193" to-port="0" />
-		<edge from-layer="193" from-port="1" to-layer="194" to-port="1" />
-		<edge from-layer="194" from-port="2" to-layer="195" to-port="1" />
-		<edge from-layer="195" from-port="2" to-layer="197" to-port="0" />
-		<edge from-layer="195" from-port="2" to-layer="217" to-port="0" />
-		<edge from-layer="196" from-port="0" to-layer="197" to-port="1" />
-		<edge from-layer="197" from-port="2" to-layer="200" to-port="0" />
-		<edge from-layer="198" from-port="0" to-layer="199" to-port="0" />
-		<edge from-layer="199" from-port="1" to-layer="200" to-port="1" />
-		<edge from-layer="200" from-port="2" to-layer="203" to-port="0" />
-		<edge from-layer="201" from-port="0" to-layer="202" to-port="0" />
-		<edge from-layer="202" from-port="1" to-layer="203" to-port="1" />
-		<edge from-layer="203" from-port="2" to-layer="206" to-port="0" />
-		<edge from-layer="204" from-port="0" to-layer="205" to-port="0" />
-		<edge from-layer="205" from-port="1" to-layer="206" to-port="1" />
-		<edge from-layer="206" from-port="2" to-layer="209" to-port="0" />
-		<edge from-layer="207" from-port="0" to-layer="208" to-port="0" />
-		<edge from-layer="208" from-port="1" to-layer="209" to-port="1" />
-		<edge from-layer="209" from-port="2" to-layer="210" to-port="0" />
-		<edge from-layer="210" from-port="1" to-layer="213" to-port="0" />
-		<edge from-layer="211" from-port="0" to-layer="212" to-port="0" />
-		<edge from-layer="212" from-port="1" to-layer="213" to-port="1" />
-		<edge from-layer="213" from-port="2" to-layer="216" to-port="0" />
-		<edge from-layer="214" from-port="0" to-layer="215" to-port="0" />
-		<edge from-layer="215" from-port="1" to-layer="216" to-port="1" />
-		<edge from-layer="216" from-port="2" to-layer="217" to-port="1" />
-		<edge from-layer="217" from-port="2" to-layer="273" to-port="0" />
+		<edge from-layer="183" from-port="2" to-layer="185" to-port="0" />
+		<edge from-layer="184" from-port="0" to-layer="185" to-port="1" />
+		<edge from-layer="185" from-port="2" to-layer="187" to-port="0" />
+		<edge from-layer="186" from-port="0" to-layer="187" to-port="1" />
+		<edge from-layer="187" from-port="2" to-layer="188" to-port="0" />
+		<edge from-layer="188" from-port="3" to-layer="190" to-port="0" />
+		<edge from-layer="189" from-port="0" to-layer="190" to-port="1" />
+		<edge from-layer="190" from-port="2" to-layer="192" to-port="0" />
+		<edge from-layer="191" from-port="0" to-layer="192" to-port="1" />
+		<edge from-layer="192" from-port="2" to-layer="194" to-port="0" />
+		<edge from-layer="193" from-port="0" to-layer="194" to-port="1" />
+		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
+		<edge from-layer="195" from-port="0" to-layer="196" to-port="1" />
+		<edge from-layer="196" from-port="2" to-layer="197" to-port="1" />
+		<edge from-layer="197" from-port="2" to-layer="213" to-port="0" />
+		<edge from-layer="197" from-port="2" to-layer="199" to-port="0" />
+		<edge from-layer="198" from-port="0" to-layer="199" to-port="1" />
+		<edge from-layer="199" from-port="2" to-layer="201" to-port="0" />
+		<edge from-layer="200" from-port="0" to-layer="201" to-port="1" />
+		<edge from-layer="201" from-port="2" to-layer="203" to-port="0" />
+		<edge from-layer="202" from-port="0" to-layer="203" to-port="1" />
+		<edge from-layer="203" from-port="2" to-layer="205" to-port="0" />
+		<edge from-layer="204" from-port="0" to-layer="205" to-port="1" />
+		<edge from-layer="205" from-port="2" to-layer="207" to-port="0" />
+		<edge from-layer="206" from-port="0" to-layer="207" to-port="1" />
+		<edge from-layer="207" from-port="2" to-layer="208" to-port="0" />
+		<edge from-layer="208" from-port="1" to-layer="210" to-port="0" />
+		<edge from-layer="209" from-port="0" to-layer="210" to-port="1" />
+		<edge from-layer="210" from-port="2" to-layer="212" to-port="0" />
+		<edge from-layer="211" from-port="0" to-layer="212" to-port="1" />
+		<edge from-layer="212" from-port="2" to-layer="213" to-port="1" />
+		<edge from-layer="213" from-port="2" to-layer="266" to-port="0" />
+		<edge from-layer="213" from-port="2" to-layer="215" to-port="0" />
+		<edge from-layer="214" from-port="0" to-layer="215" to-port="1" />
+		<edge from-layer="215" from-port="2" to-layer="217" to-port="0" />
+		<edge from-layer="216" from-port="0" to-layer="217" to-port="1" />
 		<edge from-layer="217" from-port="2" to-layer="219" to-port="0" />
 		<edge from-layer="218" from-port="0" to-layer="219" to-port="1" />
-		<edge from-layer="219" from-port="2" to-layer="222" to-port="0" />
-		<edge from-layer="220" from-port="0" to-layer="221" to-port="0" />
-		<edge from-layer="221" from-port="1" to-layer="222" to-port="1" />
-		<edge from-layer="222" from-port="2" to-layer="225" to-port="0" />
-		<edge from-layer="223" from-port="0" to-layer="224" to-port="0" />
-		<edge from-layer="224" from-port="1" to-layer="225" to-port="1" />
-		<edge from-layer="225" from-port="2" to-layer="251" to-port="0" />
-		<edge from-layer="225" from-port="2" to-layer="239" to-port="0" />
-		<edge from-layer="225" from-port="2" to-layer="228" to-port="0" />
-		<edge from-layer="226" from-port="0" to-layer="227" to-port="0" />
-		<edge from-layer="227" from-port="1" to-layer="228" to-port="1" />
-		<edge from-layer="228" from-port="2" to-layer="231" to-port="0" />
-		<edge from-layer="229" from-port="0" to-layer="230" to-port="0" />
-		<edge from-layer="230" from-port="1" to-layer="231" to-port="1" />
-		<edge from-layer="231" from-port="2" to-layer="233" to-port="0" />
-		<edge from-layer="232" from-port="0" to-layer="233" to-port="1" />
-		<edge from-layer="233" from-port="2" to-layer="235" to-port="0" />
-		<edge from-layer="234" from-port="0" to-layer="235" to-port="1" />
+		<edge from-layer="219" from-port="2" to-layer="250" to-port="0" />
+		<edge from-layer="219" from-port="2" to-layer="221" to-port="0" />
+		<edge from-layer="219" from-port="2" to-layer="240" to-port="0" />
+		<edge from-layer="220" from-port="0" to-layer="221" to-port="1" />
+		<edge from-layer="221" from-port="2" to-layer="223" to-port="0" />
+		<edge from-layer="222" from-port="0" to-layer="223" to-port="1" />
+		<edge from-layer="223" from-port="2" to-layer="225" to-port="0" />
+		<edge from-layer="224" from-port="0" to-layer="225" to-port="1" />
+		<edge from-layer="225" from-port="2" to-layer="227" to-port="0" />
+		<edge from-layer="226" from-port="0" to-layer="227" to-port="1" />
+		<edge from-layer="227" from-port="2" to-layer="228" to-port="1" />
+		<edge from-layer="228" from-port="2" to-layer="229" to-port="0" />
+		<edge from-layer="228" from-port="2" to-layer="257" to-port="2" />
+		<edge from-layer="230" from-port="0" to-layer="235" to-port="0" />
+		<edge from-layer="231" from-port="0" to-layer="234" to-port="1" />
+		<edge from-layer="232" from-port="0" to-layer="234" to-port="2" />
+		<edge from-layer="233" from-port="0" to-layer="234" to-port="3" />
+		<edge from-layer="234" from-port="4" to-layer="235" to-port="1" />
 		<edge from-layer="235" from-port="2" to-layer="236" to-port="0" />
-		<edge from-layer="235" from-port="2" to-layer="262" to-port="1" />
-		<edge from-layer="237" from-port="0" to-layer="238" to-port="0" />
-		<edge from-layer="238" from-port="1" to-layer="239" to-port="1" />
-		<edge from-layer="239" from-port="2" to-layer="241" to-port="0" />
-		<edge from-layer="240" from-port="0" to-layer="241" to-port="1" />
-		<edge from-layer="241" from-port="2" to-layer="243" to-port="0" />
-		<edge from-layer="242" from-port="0" to-layer="243" to-port="1" />
-		<edge from-layer="243" from-port="2" to-layer="259" to-port="1" />
-		<edge from-layer="243" from-port="2" to-layer="244" to-port="0" />
-		<edge from-layer="249" from-port="0" to-layer="250" to-port="0" />
-		<edge from-layer="250" from-port="1" to-layer="251" to-port="1" />
-		<edge from-layer="251" from-port="2" to-layer="254" to-port="0" />
-		<edge from-layer="252" from-port="0" to-layer="253" to-port="0" />
-		<edge from-layer="253" from-port="1" to-layer="254" to-port="1" />
+		<edge from-layer="236" from-port="1" to-layer="238" to-port="0" />
+		<edge from-layer="237" from-port="0" to-layer="238" to-port="2" />
+		<edge from-layer="238" from-port="3" to-layer="245" to-port="0" />
+		<edge from-layer="239" from-port="0" to-layer="240" to-port="1" />
+		<edge from-layer="240" from-port="2" to-layer="242" to-port="0" />
+		<edge from-layer="241" from-port="0" to-layer="242" to-port="1" />
+		<edge from-layer="242" from-port="2" to-layer="244" to-port="0" />
+		<edge from-layer="243" from-port="0" to-layer="244" to-port="1" />
+		<edge from-layer="244" from-port="2" to-layer="245" to-port="1" />
+		<edge from-layer="245" from-port="2" to-layer="246" to-port="0" />
+		<edge from-layer="245" from-port="2" to-layer="257" to-port="1" />
+		<edge from-layer="249" from-port="0" to-layer="250" to-port="1" />
+		<edge from-layer="250" from-port="2" to-layer="252" to-port="0" />
+		<edge from-layer="251" from-port="0" to-layer="252" to-port="1" />
+		<edge from-layer="252" from-port="2" to-layer="254" to-port="0" />
+		<edge from-layer="253" from-port="0" to-layer="254" to-port="1" />
 		<edge from-layer="254" from-port="2" to-layer="256" to-port="0" />
 		<edge from-layer="255" from-port="0" to-layer="256" to-port="1" />
-		<edge from-layer="256" from-port="2" to-layer="258" to-port="0" />
-		<edge from-layer="257" from-port="0" to-layer="258" to-port="1" />
-		<edge from-layer="258" from-port="2" to-layer="259" to-port="0" />
-		<edge from-layer="259" from-port="2" to-layer="260" to-port="0" />
-		<edge from-layer="260" from-port="2" to-layer="261" to-port="0" />
-		<edge from-layer="261" from-port="1" to-layer="262" to-port="0" />
-		<edge from-layer="262" from-port="2" to-layer="264" to-port="0" />
-		<edge from-layer="263" from-port="0" to-layer="264" to-port="1" />
-		<edge from-layer="264" from-port="2" to-layer="266" to-port="0" />
-		<edge from-layer="265" from-port="0" to-layer="266" to-port="1" />
-		<edge from-layer="266" from-port="2" to-layer="269" to-port="0" />
-		<edge from-layer="267" from-port="0" to-layer="268" to-port="0" />
-		<edge from-layer="268" from-port="1" to-layer="269" to-port="1" />
-		<edge from-layer="269" from-port="2" to-layer="272" to-port="0" />
-		<edge from-layer="270" from-port="0" to-layer="271" to-port="0" />
-		<edge from-layer="271" from-port="1" to-layer="272" to-port="1" />
-		<edge from-layer="272" from-port="2" to-layer="273" to-port="1" />
-		<edge from-layer="273" from-port="2" to-layer="305" to-port="0" />
-		<edge from-layer="273" from-port="2" to-layer="275" to-port="0" />
-		<edge from-layer="274" from-port="0" to-layer="275" to-port="1" />
-		<edge from-layer="275" from-port="2" to-layer="278" to-port="0" />
-		<edge from-layer="276" from-port="0" to-layer="277" to-port="0" />
-		<edge from-layer="277" from-port="1" to-layer="278" to-port="1" />
-		<edge from-layer="278" from-port="2" to-layer="281" to-port="0" />
-		<edge from-layer="279" from-port="0" to-layer="280" to-port="0" />
-		<edge from-layer="280" from-port="1" to-layer="281" to-port="1" />
-		<edge from-layer="281" from-port="2" to-layer="284" to-port="0" />
-		<edge from-layer="282" from-port="0" to-layer="283" to-port="0" />
-		<edge from-layer="283" from-port="1" to-layer="284" to-port="1" />
-		<edge from-layer="284" from-port="2" to-layer="287" to-port="0" />
-		<edge from-layer="285" from-port="0" to-layer="286" to-port="0" />
-		<edge from-layer="286" from-port="1" to-layer="287" to-port="1" />
+		<edge from-layer="256" from-port="2" to-layer="257" to-port="0" />
+		<edge from-layer="257" from-port="4" to-layer="259" to-port="0" />
+		<edge from-layer="258" from-port="0" to-layer="259" to-port="1" />
+		<edge from-layer="259" from-port="2" to-layer="261" to-port="0" />
+		<edge from-layer="260" from-port="0" to-layer="261" to-port="1" />
+		<edge from-layer="261" from-port="2" to-layer="263" to-port="0" />
+		<edge from-layer="262" from-port="0" to-layer="263" to-port="1" />
+		<edge from-layer="263" from-port="2" to-layer="265" to-port="0" />
+		<edge from-layer="264" from-port="0" to-layer="265" to-port="1" />
+		<edge from-layer="265" from-port="2" to-layer="266" to-port="1" />
+		<edge from-layer="266" from-port="2" to-layer="290" to-port="0" />
+		<edge from-layer="266" from-port="2" to-layer="268" to-port="0" />
+		<edge from-layer="267" from-port="0" to-layer="268" to-port="1" />
+		<edge from-layer="268" from-port="2" to-layer="270" to-port="0" />
+		<edge from-layer="269" from-port="0" to-layer="270" to-port="1" />
+		<edge from-layer="270" from-port="2" to-layer="272" to-port="0" />
+		<edge from-layer="271" from-port="0" to-layer="272" to-port="1" />
+		<edge from-layer="272" from-port="2" to-layer="274" to-port="0" />
+		<edge from-layer="273" from-port="0" to-layer="274" to-port="1" />
+		<edge from-layer="274" from-port="2" to-layer="276" to-port="0" />
+		<edge from-layer="275" from-port="0" to-layer="276" to-port="1" />
+		<edge from-layer="276" from-port="2" to-layer="278" to-port="0" />
+		<edge from-layer="277" from-port="0" to-layer="278" to-port="1" />
+		<edge from-layer="278" from-port="2" to-layer="280" to-port="0" />
+		<edge from-layer="279" from-port="0" to-layer="280" to-port="1" />
+		<edge from-layer="280" from-port="2" to-layer="281" to-port="0" />
+		<edge from-layer="281" from-port="3" to-layer="283" to-port="0" />
+		<edge from-layer="282" from-port="0" to-layer="283" to-port="1" />
+		<edge from-layer="283" from-port="2" to-layer="285" to-port="0" />
+		<edge from-layer="284" from-port="0" to-layer="285" to-port="1" />
+		<edge from-layer="285" from-port="2" to-layer="287" to-port="0" />
+		<edge from-layer="286" from-port="0" to-layer="287" to-port="1" />
 		<edge from-layer="287" from-port="2" to-layer="289" to-port="0" />
 		<edge from-layer="288" from-port="0" to-layer="289" to-port="1" />
-		<edge from-layer="289" from-port="2" to-layer="291" to-port="0" />
-		<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
-		<edge from-layer="291" from-port="2" to-layer="292" to-port="0" />
-		<edge from-layer="292" from-port="2" to-layer="293" to-port="0" />
-		<edge from-layer="293" from-port="1" to-layer="294" to-port="0" />
+		<edge from-layer="289" from-port="2" to-layer="290" to-port="1" />
+		<edge from-layer="290" from-port="2" to-layer="306" to-port="0" />
+		<edge from-layer="290" from-port="2" to-layer="292" to-port="0" />
+		<edge from-layer="291" from-port="0" to-layer="292" to-port="1" />
+		<edge from-layer="292" from-port="2" to-layer="294" to-port="0" />
+		<edge from-layer="293" from-port="0" to-layer="294" to-port="1" />
 		<edge from-layer="294" from-port="2" to-layer="296" to-port="0" />
 		<edge from-layer="295" from-port="0" to-layer="296" to-port="1" />
 		<edge from-layer="296" from-port="2" to-layer="298" to-port="0" />
 		<edge from-layer="297" from-port="0" to-layer="298" to-port="1" />
-		<edge from-layer="298" from-port="2" to-layer="301" to-port="0" />
-		<edge from-layer="299" from-port="0" to-layer="300" to-port="0" />
-		<edge from-layer="300" from-port="1" to-layer="301" to-port="1" />
-		<edge from-layer="301" from-port="2" to-layer="304" to-port="0" />
-		<edge from-layer="302" from-port="0" to-layer="303" to-port="0" />
-		<edge from-layer="303" from-port="1" to-layer="304" to-port="1" />
-		<edge from-layer="304" from-port="2" to-layer="305" to-port="1" />
-		<edge from-layer="305" from-port="2" to-layer="327" to-port="0" />
-		<edge from-layer="305" from-port="2" to-layer="307" to-port="0" />
-		<edge from-layer="306" from-port="0" to-layer="307" to-port="1" />
-		<edge from-layer="307" from-port="2" to-layer="310" to-port="0" />
-		<edge from-layer="308" from-port="0" to-layer="309" to-port="0" />
-		<edge from-layer="309" from-port="1" to-layer="310" to-port="1" />
-		<edge from-layer="310" from-port="2" to-layer="313" to-port="0" />
-		<edge from-layer="311" from-port="0" to-layer="312" to-port="0" />
-		<edge from-layer="312" from-port="1" to-layer="313" to-port="1" />
-		<edge from-layer="313" from-port="2" to-layer="316" to-port="0" />
-		<edge from-layer="314" from-port="0" to-layer="315" to-port="0" />
-		<edge from-layer="315" from-port="1" to-layer="316" to-port="1" />
-		<edge from-layer="316" from-port="2" to-layer="319" to-port="0" />
-		<edge from-layer="317" from-port="0" to-layer="318" to-port="0" />
-		<edge from-layer="318" from-port="1" to-layer="319" to-port="1" />
-		<edge from-layer="319" from-port="2" to-layer="320" to-port="0" />
-		<edge from-layer="320" from-port="1" to-layer="323" to-port="0" />
-		<edge from-layer="321" from-port="0" to-layer="322" to-port="0" />
-		<edge from-layer="322" from-port="1" to-layer="323" to-port="1" />
-		<edge from-layer="323" from-port="2" to-layer="326" to-port="0" />
-		<edge from-layer="324" from-port="0" to-layer="325" to-port="0" />
-		<edge from-layer="325" from-port="1" to-layer="326" to-port="1" />
-		<edge from-layer="326" from-port="2" to-layer="327" to-port="1" />
-		<edge from-layer="327" from-port="2" to-layer="329" to-port="0" />
-		<edge from-layer="328" from-port="0" to-layer="329" to-port="1" />
-		<edge from-layer="329" from-port="2" to-layer="332" to-port="0" />
-		<edge from-layer="330" from-port="0" to-layer="331" to-port="0" />
-		<edge from-layer="331" from-port="1" to-layer="332" to-port="1" />
-		<edge from-layer="332" from-port="2" to-layer="335" to-port="0" />
-		<edge from-layer="333" from-port="0" to-layer="334" to-port="0" />
-		<edge from-layer="334" from-port="1" to-layer="335" to-port="1" />
-		<edge from-layer="335" from-port="2" to-layer="336" to-port="0" />
-		<edge from-layer="336" from-port="2" to-layer="337" to-port="0" />
+		<edge from-layer="298" from-port="2" to-layer="300" to-port="0" />
+		<edge from-layer="299" from-port="0" to-layer="300" to-port="1" />
+		<edge from-layer="300" from-port="2" to-layer="301" to-port="0" />
+		<edge from-layer="301" from-port="1" to-layer="303" to-port="0" />
+		<edge from-layer="302" from-port="0" to-layer="303" to-port="1" />
+		<edge from-layer="303" from-port="2" to-layer="305" to-port="0" />
+		<edge from-layer="304" from-port="0" to-layer="305" to-port="1" />
+		<edge from-layer="305" from-port="2" to-layer="306" to-port="1" />
+		<edge from-layer="306" from-port="2" to-layer="308" to-port="0" />
+		<edge from-layer="307" from-port="0" to-layer="308" to-port="1" />
+		<edge from-layer="308" from-port="2" to-layer="310" to-port="0" />
+		<edge from-layer="309" from-port="0" to-layer="310" to-port="1" />
+		<edge from-layer="310" from-port="2" to-layer="312" to-port="0" />
+		<edge from-layer="311" from-port="0" to-layer="312" to-port="1" />
+		<edge from-layer="312" from-port="2" to-layer="313" to-port="0" />
+		<edge from-layer="313" from-port="2" to-layer="314" to-port="0" />
 	</edges>
 	<rt_info>
-		<Runtime_version value="2024.5.0-17285-ea5c1dcfdf9-releases/2024/5" />
+		<Runtime_version value="2025.2.0-19120-87425bc78ca-releases/2025/2" />
 		<conversion_parameters>
 			<framework value="pytorch" />
 			<is_python_object value="True" />
 		</conversion_parameters>
 		<optimum>
-			<optimum_intel_version value="1.21.0.dev0+d357376" />
-			<optimum_version value="1.23.3" />
-			<pytorch_version value="2.5.1" />
-			<transformers_version value="4.46.3" />
+			<optimum_intel_version value="1.24.0.dev0+08e3008" />
+			<optimum_version value="1.25.3" />
+			<pytorch_version value="2.7.0+cpu" />
+			<transformers_version value="4.51.3" />
 		</optimum>
+		<runtime_options>
+			<ACTIVATIONS_SCALE_FACTOR value="8.0" />
+			<KV_CACHE_PRECISION value="f16" />
+		</runtime_options>
 	</rt_info>
 </net>