diff --git "a/openvino_decoder_model.xml" "b/openvino_decoder_model.xml"
new file mode 100644--- /dev/null
+++ "b/openvino_decoder_model.xml"
@@ -0,0 +1,20187 @@
+<?xml version="1.0"?>
+<net name="Model3" version="11">
+	<layers>
+		<layer id="1" name="decoder_input_ids" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="input_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="0" name="Parameter_12156" type="Parameter" version="opset1">
+			<data shape="?,?,?" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="encoder_hidden_states">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="self.model.model.decoder.embed_tokens.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="51865, 512" offset="0" size="26554880" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Convert_23789" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.model.model.decoder.embed_tokens.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="51865, 1" offset="26554880" size="51865" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>51865</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Convert_23792" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>51865</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>51865</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="self.model.model.decoder.embed_tokens.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>51865</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="self.model.model.decoder.embed_tokens.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="51865, 1" offset="26606745" size="103730" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>51865</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>51865</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Constant_18834" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="26710475" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="__module.model.model.decoder/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<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="I64" names="54">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="__module.model.model.decoder.embed_tokens/aten::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<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="13" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26710491" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="14" name="__module.model.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="56,inputs_embeds">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="self.model.model.decoder.embed_positions.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="448, 512" offset="26710495" size="229376" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Convert_24460" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="self.model.model.decoder.embed_positions.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="448, 1" offset="26939871" size="448" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>448</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="Convert_24463" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>448</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>448</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="self.model.model.decoder.embed_positions.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>448</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="self.model.model.decoder.embed_positions.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="448, 1" offset="26940319" size="896" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>448</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="self.model.model.decoder.embed_positions.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>448</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="self.model.model.decoder.embed_positions.weight/fq_weights_0/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>448</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="23" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64" names="23" />
+			</output>
+		</layer>
+		<layer id="24" name="ShapeOf_18807" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_18808" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="26" name="Constant_18809" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="27" name="Gather_18810" 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="51,57,67,69" />
+			</output>
+		</layer>
+		<layer id="28" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26941231" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="29" 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="59,cache_position">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" 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="60,position_ids">
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" 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="32" name="Constant_12153" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26710491" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="33" 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>512</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="63,64,positions,positions.1">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="__module.model.model.decoder/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="65,input.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" 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="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="Constant_18427" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="26941239" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="39" name="Constant_18428" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="26943287" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="40" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="98,hidden_states.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="41" name="Constant_18198" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="26945335" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="42" name="Convert_24085" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="43" name="Constant_18198/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27076407" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="44" name="Convert_24087" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="Constant_18198/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="Constant_18198/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27077431" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="Constant_18198/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="48" name="Constant_24092" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="49" name="Reshape_24093" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="50" name="Constant_18198/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="51" name="Multiply_18149" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="52" name="Constant_18429" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27081543" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="53" name="__module.model.model.decoder.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="108,tensor.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="54" name="Constant_18835" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="55" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="110">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="56" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="57" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="111">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="58" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27083639" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="59" name="Convert_24074" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="60" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27214711" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="61" name="Convert_24076" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="62" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="63" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27215735" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="64" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="65" name="Constant_24081" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="66" name="Reshape_24082" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="67" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="68" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="114,tensor.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="69" name="Constant_18836" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="70" 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>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="116">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="71" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="72" 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>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="117">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="73" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="127,attn_weights.1">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="74" name="__module.model.model.decoder/aten::triu/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26710491" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="75" name="__module.model.model.decoder/aten::full/Convert" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="27219831" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="76" name="Constant_18817" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="77" name="Reshape_18818" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="78" name="__module.model.model.decoder/aten::add/Multiply_3" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="79" 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="70,72" />
+			</output>
+		</layer>
+		<layer id="80" name="Constant_6217" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26710491" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="81" name="Unsqueeze_6218" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="82" name="__module.model.model.decoder/prim::ListConstruct_1" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="83" name="__module.model.model.decoder/aten::full/Broadcast" type="Broadcast" version="opset3">
+			<data mode="numpy" />
+			<input>
+				<port id="0" precision="FP32" />
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="75">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="84" name="ShapeOf_18819" type="ShapeOf" version="opset3">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="85" name="Constant_18820" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="86" name="Constant_18821" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="87" name="Gather_18822" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I32" />
+			</output>
+		</layer>
+		<layer id="88" name="__module.model.model.decoder/aten::triu/Constant_2" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26941231" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="89" name="__module.model.model.decoder/aten::triu/Range" 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>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="90" name="__module.model.model.decoder/aten::triu/Unsqueeze" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="91" name="__module.model.model.decoder/aten::triu/Convert" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26941231" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="92" name="Convert_18825" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64" />
+			</input>
+			<output>
+				<port id="1" precision="I32" />
+			</output>
+		</layer>
+		<layer id="93" name="__module.model.model.decoder/aten::triu/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32" />
+			</output>
+		</layer>
+		<layer id="94" 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>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="95" name="__module.model.model.decoder/aten::triu/Unsqueeze_1" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="96" name="__module.model.model.decoder/aten::triu/GreaterEqual" type="GreaterEqual" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="97" name="__module.model.model.decoder/aten::triu/ConvertLike" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="26710491" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="98" name="__module.model.model.decoder/aten::triu/Select" type="Select" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="FP32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="76_1">
+					<dim>-1</dim>
+					<dim>-1</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="26710491" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="100" name="__module.model.model.decoder/aten::arange/Constant_2" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="26941231" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</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>
+			<output>
+				<port id="3" precision="FP32">
+					<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>
+			<output>
+				<port id="1" precision="I64" names="77">
+					<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" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="104" name="Constant_6320" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27219835" size="16" />
+			<output>
+				<port id="0" precision="I64" names="78">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="105" 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>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="79">
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="106" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL" names="80">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="107" name="__module.model.model.decoder/aten::mul_/ConvertLike" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="108" name="__module.model.model.decoder/aten::mul_/Multiply" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="76,causal_mask.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="109" 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>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="82">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="110" name="28" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64" names="28" />
+			</output>
+		</layer>
+		<layer id="111" 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>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="83,84,85">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="112" name="Constant_18814" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="113" name="Constant_18815" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="114" name="Gather_18816" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64" names="103,153,218,268,333,383,448,498,563,613,678,728,73">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="115" name="Constant_17086" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="116" name="Constant_17088" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="117" name="Constant_17090" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="118" name="__module.model.model.decoder/prim::ListConstruct_2" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<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="4" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="119" 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>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="129,130,131,244,245,246,359,360,361,474,475,476,589,590,591,704,705,706,87,attention_mask">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="120" name="Constant_6754" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="121" name="ShapeOf_18830" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="122" name="Constant_18831" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="123" name="Constant_18832" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="26941215" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="124" name="Gather_18833" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64" names="128,243,358,473,588,703">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="125" name="Constant_6757" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="26941223" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="126" name="__module.model.model.decoder/aten::slice/Reshape_1" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="27219851" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="127" 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>-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>
+				<port id="4" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="5" precision="FP32" names="132,247,362,477,592,707,causal_mask,causal_mask.11,causal_mask.13,causal_mask.5,causal_mask.7,causal_mask.9">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="128" name="__module.model.model.decoder.layers.0.self_attn/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="133,input.3">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="129" name="__module.model.model.decoder.layers.0.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="134,input.5">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="130" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27219859" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="131" name="Convert_24063" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="132" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27350931" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="133" name="Convert_24065" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="134" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="135" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27351955" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="136" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="137" name="Constant_24070" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="138" name="Reshape_24071" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="139" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="140" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="141" name="Constant_18430" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27356051" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="142" 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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="121,tensor.5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="143" name="Constant_18837" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="144" 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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="123">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="145" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="146" 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>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="124">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="147" name="__module.model.model.decoder.layers.0.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="136,attn_output.1">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="148" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="149" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="137,attn_output.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="150" name="Constant_18838" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27358099" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="151" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="139">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="152" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27358123" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="153" name="Convert_24096" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="154" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27489195" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="155" name="Convert_24098" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="156" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="157" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27490219" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="158" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="159" name="Constant_24103" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="160" name="Reshape_24104" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="161" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="162" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="163" name="Constant_18431" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27494315" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="164" 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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="142,input.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="165" 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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="144,residual.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="166" 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="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="167" 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>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="168" name="Constant_18432" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27496363" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="169" 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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="170" name="Constant_18433" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27498411" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="171" 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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="148,hidden_states.5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="172" name="Constant_18201" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27500459" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="173" name="Convert_24107" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="174" name="Constant_18201/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27631531" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="175" name="Convert_24109" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="176" name="Constant_18201/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="177" name="Constant_18201/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27632555" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="178" name="Constant_18201/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="179" name="Constant_24114" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="180" name="Reshape_24115" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="181" name="Constant_18201/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="182" name="Multiply_18153" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="183" name="Constant_18434" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27636651" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="184" name="__module.model.model.decoder.layers.0.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="158,tensor.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="185" name="Constant_18839" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="186" 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>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="160">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="187" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="188" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="161">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="189" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27638699" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="190" name="Convert_24052" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="191" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27769771" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="192" name="Convert_24054" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="193" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="194" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27770795" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="195" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="196" name="Constant_24059" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="197" name="Reshape_24060" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="198" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="199" 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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="164,tensor.9">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="200" name="Constant_6978" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="27774891" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="201" name="Constant_6979" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="27774899" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="202" name="Constant_6980" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="27774907" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="203" name="__module.model.model.decoder.layers.0.encoder_attn/prim::ListConstruct_1" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<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="4" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="204" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="166">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="205" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="206" 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>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="167">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="207" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="177,input.9">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="208" name="__module.model.model.decoder.layers.0.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="178,input.11">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="209" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27774915" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="210" name="Convert_24041" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="211" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="27905987" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="212" name="Convert_24043" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="213" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="214" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="27907011" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="215" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="216" name="Constant_24048" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="217" name="Reshape_24049" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="218" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="219" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="220" name="Constant_18435" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="27911107" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="221" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="171,tensor.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="222" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="173">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="223" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="224" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="174">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="225" name="__module.model.model.decoder.layers.0.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="180,attn_output.5">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="226" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="227" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="181,attn_output.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="228" name="Constant_18840" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27913155" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="229" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="183">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="230" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="27913179" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="231" name="Convert_24118" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="232" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="28044251" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="233" name="Convert_24120" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="234" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="235" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="28045275" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="236" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="237" name="Constant_24125" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="238" name="Reshape_24126" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="239" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="240" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="241" name="Constant_18436" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="28049371" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="242" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="186,input.13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="243" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="188,residual.5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="244" 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="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="245" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="246" name="Constant_18437" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="28051419" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="247" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="248" name="Constant_18438" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="28053467" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="249" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="192">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="250" name="self.model.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 128" offset="28055515" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="251" name="Convert_23799" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="252" name="self.model.model.decoder.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 1" offset="28579803" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="253" name="Convert_23801" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="254" name="self.model.model.decoder.layers.0.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="255" name="self.model.model.decoder.layers.0.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 4, 1" offset="28583899" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="256" name="self.model.model.decoder.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="257" name="Constant_23806" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="28600283" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="258" name="Reshape_23807" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="259" name="self.model.model.decoder.layers.0.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="260" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="261" name="Constant_18439" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 2048" offset="28600299" size="8192" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="262" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="195">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="263" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="196,input.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="264" name="self.model.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 128" offset="28608491" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="265" name="Convert_23810" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="266" name="self.model.model.decoder.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 1" offset="29132779" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="267" name="Convert_23812" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="268" name="self.model.model.decoder.layers.0.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="269" name="self.model.model.decoder.layers.0.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 16, 1" offset="29136875" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="270" name="self.model.model.decoder.layers.0.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="271" name="Constant_23817" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="29153259" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="272" name="Reshape_23818" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="273" name="self.model.model.decoder.layers.0.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="274" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="275" name="Constant_18440" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29153275" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="276" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="200,input.17">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="277" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="202,residual.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="278" 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="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="279" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="280" name="Constant_18441" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29155323" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="281" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="282" name="Constant_18442" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29157371" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="283" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="213,hidden_states.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="284" name="Constant_18204" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29159419" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="285" name="Convert_24151" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="286" name="Constant_18204/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="29290491" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="287" name="Convert_24153" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="288" name="Constant_18204/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="289" name="Constant_18204/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="29291515" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="290" name="Constant_18204/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="291" name="Constant_24158" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="292" name="Reshape_24159" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="293" name="Constant_18204/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="294" name="Multiply_18157" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="295" name="Constant_18443" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29295611" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="296" name="__module.model.model.decoder.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="223,tensor.13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="297" name="Constant_18841" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="298" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="225">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="299" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="300" 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>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="226">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="301" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29297659" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="302" name="Convert_24140" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="303" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="29428731" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="304" name="Convert_24142" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="305" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="306" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="29429755" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="307" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="308" name="Constant_24147" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="309" name="Reshape_24148" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="310" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="311" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="229,tensor.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="312" name="Constant_18842" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="313" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="231">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="314" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="315" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="232">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="316" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="242,attn_weights.3">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="317" 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">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="248,input.19">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="318" 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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="249,input.21">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="319" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29433851" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="320" name="Convert_24129" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="321" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="29564923" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="322" name="Convert_24131" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="323" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="324" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="29565947" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="325" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="326" name="Constant_24136" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="327" name="Reshape_24137" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="328" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="329" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="330" name="Constant_18444" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29570043" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="331" 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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="236,tensor.17">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="332" name="Constant_18843" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="333" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="238">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="334" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="335" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="239">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="336" 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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="251,attn_output.9">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="337" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="338" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="252,attn_output.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="339" name="Constant_18844" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27358099" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="340" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="254">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="341" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29572091" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="342" name="Convert_24162" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="343" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="29703163" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="344" name="Convert_24164" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="345" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="346" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="29704187" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="347" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="348" name="Constant_24169" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="349" name="Reshape_24170" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="350" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="351" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="352" name="Constant_18445" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29708283" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="353" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="257,input.23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="354" name="__module.model.model.decoder.layers.1/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="259,residual.9">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="355" 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="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="356" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="357" name="Constant_18446" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29710331" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="358" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="359" name="Constant_18447" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29712379" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="360" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="263,hidden_states.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="361" name="Constant_18207" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29714427" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="362" name="Convert_24173" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="363" name="Constant_18207/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="29845499" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="364" name="Convert_24175" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="365" name="Constant_18207/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="366" name="Constant_18207/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="29846523" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="367" name="Constant_18207/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="368" name="Constant_24180" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="369" name="Reshape_24181" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="370" name="Constant_18207/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="371" name="Multiply_18161" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="372" name="Constant_18448" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29850619" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="373" name="__module.model.model.decoder.layers.1.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="273,tensor.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="374" name="Constant_18845" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="375" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="275">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="376" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="377" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="276">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="378" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29852667" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="379" name="Convert_24030" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="380" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="29983739" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="381" name="Convert_24032" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="382" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="383" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="29984763" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="384" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="385" name="Constant_24037" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="386" name="Reshape_24038" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="387" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="388" 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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="279,tensor.21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="389" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="281">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="390" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="391" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="282">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="392" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="292,input.25">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="393" 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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="293,input.27">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="394" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="29988859" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="395" name="Convert_24019" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="396" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="30119931" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="397" name="Convert_24021" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="398" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="399" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="30120955" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="400" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="401" name="Constant_24026" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="402" name="Reshape_24027" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="403" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="404" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="405" name="Constant_18449" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="30125051" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="406" 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="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="286,tensor.23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="407" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="288">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="408" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="409" 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>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="289">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="410" 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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="295,attn_output.13">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="411" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="412" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="296,attn_output.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="413" name="Constant_18846" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27913155" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="414" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="298">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="415" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="30127099" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="416" name="Convert_24184" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="417" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="30258171" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="418" name="Convert_24186" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="419" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="420" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="30259195" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="421" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="422" name="Constant_24191" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="423" name="Reshape_24192" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="424" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="425" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="426" name="Constant_18450" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="30263291" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="427" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="301,input.29">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="428" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="303,residual.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="429" 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="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="430" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="431" name="Constant_18451" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="30265339" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="432" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="433" name="Constant_18452" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="30267387" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="434" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="307">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="435" name="self.model.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 128" offset="30269435" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="436" name="Convert_23821" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="437" name="self.model.model.decoder.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 1" offset="30793723" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="438" name="Convert_23823" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="439" name="self.model.model.decoder.layers.1.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="440" name="self.model.model.decoder.layers.1.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 4, 1" offset="30797819" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="441" name="self.model.model.decoder.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="442" name="Constant_23828" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="28600283" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="443" name="Reshape_23829" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="444" name="self.model.model.decoder.layers.1.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="445" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="446" name="Constant_18453" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 2048" offset="30814203" size="8192" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="447" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="310">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="448" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="311,input.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="449" name="self.model.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 128" offset="30822395" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="450" name="Convert_23832" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="451" name="self.model.model.decoder.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 1" offset="31346683" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="452" name="Convert_23834" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="453" name="self.model.model.decoder.layers.1.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="454" name="self.model.model.decoder.layers.1.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 16, 1" offset="31350779" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="455" name="self.model.model.decoder.layers.1.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="456" name="Constant_23839" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="29153259" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="457" name="Reshape_23840" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="458" name="self.model.model.decoder.layers.1.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="459" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="460" name="Constant_18454" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31367163" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="461" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="315,input.33">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="462" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="317,residual.13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="463" name="__module.model.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="464" name="__module.model.model.decoder.layers.2.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="465" name="Constant_18455" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31369211" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="466" name="__module.model.model.decoder.layers.2.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="467" name="Constant_18456" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31371259" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="468" name="__module.model.model.decoder.layers.2.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="328,hidden_states.21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="469" name="Constant_18210" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="31373307" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="470" name="Convert_24217" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="471" name="Constant_18210/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="31504379" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="472" name="Convert_24219" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="473" name="Constant_18210/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="474" name="Constant_18210/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="31505403" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="475" name="Constant_18210/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="476" name="Constant_24224" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="477" name="Reshape_24225" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="478" name="Constant_18210/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="479" name="Multiply_18165" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="480" name="Constant_18457" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31509499" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="481" name="__module.model.model.decoder.layers.2.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="338,tensor.25">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="482" name="Constant_18847" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="483" name="__module.model.model.decoder.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="340">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="484" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="485" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="341">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="486" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="31511547" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="487" name="Convert_24206" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="488" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="31642619" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="489" name="Convert_24208" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="490" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="491" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="31643643" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="492" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="493" name="Constant_24213" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="494" name="Reshape_24214" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="495" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="496" name="__module.model.model.decoder.layers.2.self_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="344,tensor.27">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="497" name="Constant_18848" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="498" name="__module.model.model.decoder.layers.2.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>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="346">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="499" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="500" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="347">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="501" name="__module.model.model.decoder.layers.2.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="357,attn_weights.5">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="502" name="__module.model.model.decoder.layers.2.self_attn/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="363,input.35">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="503" name="__module.model.model.decoder.layers.2.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="364,input.37">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="504" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="31647739" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="505" name="Convert_24195" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="506" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="31778811" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="507" name="Convert_24197" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="508" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="509" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="31779835" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="510" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="511" name="Constant_24202" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="512" name="Reshape_24203" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="513" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="514" name="__module.model.model.decoder.layers.2.self_attn.v_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="515" name="Constant_18458" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31783931" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="516" name="__module.model.model.decoder.layers.2.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="351,tensor.29">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="517" name="Constant_18849" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="518" name="__module.model.model.decoder.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="353">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="519" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="520" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="354">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="521" name="__module.model.model.decoder.layers.2.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="366,attn_output.17">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="522" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="523" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="367,attn_output.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="524" name="Constant_18850" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27358099" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="525" name="__module.model.model.decoder.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="369">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="526" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="31785979" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="527" name="Convert_24228" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="528" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="31917051" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="529" name="Convert_24230" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="530" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="531" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="31918075" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="532" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="533" name="Constant_24235" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="534" name="Reshape_24236" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="535" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="536" name="__module.model.model.decoder.layers.2.self_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="537" name="Constant_18459" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31922171" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="538" name="__module.model.model.decoder.layers.2.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="372,input.39">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="539" name="__module.model.model.decoder.layers.2/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="374,residual.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="540" name="__module.model.model.decoder.layers.2.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="541" name="__module.model.model.decoder.layers.2.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>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="542" name="Constant_18460" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31924219" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="543" name="__module.model.model.decoder.layers.2.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="544" name="Constant_18461" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="31926267" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="545" name="__module.model.model.decoder.layers.2.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="378,hidden_states.25">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="546" name="Constant_18213" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="31928315" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="547" name="Convert_24239" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="548" name="Constant_18213/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="32059387" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="549" name="Convert_24241" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="550" name="Constant_18213/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="551" name="Constant_18213/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="32060411" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="552" name="Constant_18213/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="553" name="Constant_24246" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="554" name="Reshape_24247" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="555" name="Constant_18213/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="556" name="Multiply_18169" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="557" name="Constant_18462" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="32064507" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="558" name="__module.model.model.decoder.layers.2.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="388,tensor.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="559" name="Constant_18851" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="560" name="__module.model.model.decoder.layers.2.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="390">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="561" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="562" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="391">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="563" name="self.model.model.decoder.layers.2.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="32066555" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="564" name="Convert_24008" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="565" name="self.model.model.decoder.layers.2.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="32197627" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="566" name="Convert_24010" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="567" name="self.model.model.decoder.layers.2.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="568" name="self.model.model.decoder.layers.2.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="32198651" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="569" name="self.model.model.decoder.layers.2.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="570" name="Constant_24015" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="571" name="Reshape_24016" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="572" name="self.model.model.decoder.layers.2.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="573" name="__module.model.model.decoder.layers.2.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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="394,tensor.33">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="574" name="__module.model.model.decoder.layers.2.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="396">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="575" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="576" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="397">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="577" name="__module.model.model.decoder.layers.2.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="407,input.41">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="578" name="__module.model.model.decoder.layers.2.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="408,input.43">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="579" name="self.model.model.decoder.layers.2.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="32202747" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="580" name="Convert_23997" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="581" name="self.model.model.decoder.layers.2.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="32333819" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="582" name="Convert_23999" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="583" name="self.model.model.decoder.layers.2.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="584" name="self.model.model.decoder.layers.2.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="32334843" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="585" name="self.model.model.decoder.layers.2.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="586" name="Constant_24004" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="587" name="Reshape_24005" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="588" name="self.model.model.decoder.layers.2.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="589" name="__module.model.model.decoder.layers.2.encoder_attn.v_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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="590" name="Constant_18463" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="32338939" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="591" name="__module.model.model.decoder.layers.2.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="401,tensor.35">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="592" name="__module.model.model.decoder.layers.2.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="403">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="593" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="594" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="404">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="595" name="__module.model.model.decoder.layers.2.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="410,attn_output.21">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="596" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="597" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="411,attn_output.23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="598" name="Constant_18852" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27913155" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="599" name="__module.model.model.decoder.layers.2.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="413">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="600" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="32340987" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="601" name="Convert_24250" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="602" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="32472059" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="603" name="Convert_24252" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="604" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="605" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="32473083" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="606" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="607" name="Constant_24257" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="608" name="Reshape_24258" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="609" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="610" name="__module.model.model.decoder.layers.2.encoder_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="611" name="Constant_18464" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="32477179" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="612" name="__module.model.model.decoder.layers.2.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="416,input.45">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="613" name="__module.model.model.decoder.layers.2/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="418,residual.17">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="614" name="__module.model.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="615" name="__module.model.model.decoder.layers.2.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="616" name="Constant_18465" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="32479227" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="617" name="__module.model.model.decoder.layers.2.final_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="618" name="Constant_18466" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="32481275" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="619" name="__module.model.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="422">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="620" name="self.model.model.decoder.layers.2.fc1.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 128" offset="32483323" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="621" name="Convert_23843" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="622" name="self.model.model.decoder.layers.2.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 1" offset="33007611" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="623" name="Convert_23845" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="624" name="self.model.model.decoder.layers.2.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="625" name="self.model.model.decoder.layers.2.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 4, 1" offset="33011707" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="626" name="self.model.model.decoder.layers.2.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="627" name="Constant_23850" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="28600283" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="628" name="Reshape_23851" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="629" name="self.model.model.decoder.layers.2.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="630" name="__module.model.model.decoder.layers.2.fc1/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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="631" name="Constant_18467" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 2048" offset="33028091" size="8192" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="632" name="__module.model.model.decoder.layers.2.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="425">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="633" name="__module.model.model.decoder.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="426,input.47">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="634" name="self.model.model.decoder.layers.2.fc2.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 128" offset="33036283" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="635" name="Convert_23854" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="636" name="self.model.model.decoder.layers.2.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 1" offset="33560571" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="637" name="Convert_23856" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="638" name="self.model.model.decoder.layers.2.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="639" name="self.model.model.decoder.layers.2.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 16, 1" offset="33564667" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="640" name="self.model.model.decoder.layers.2.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="641" name="Constant_23861" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="29153259" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="642" name="Reshape_23862" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="643" name="self.model.model.decoder.layers.2.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="644" name="__module.model.model.decoder.layers.2.fc2/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>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="645" name="Constant_18468" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="33581051" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="646" name="__module.model.model.decoder.layers.2.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="430,input.49">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="647" name="__module.model.model.decoder.layers.2/aten::add/Add_2" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="432,residual.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="648" name="__module.model.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="649" name="__module.model.model.decoder.layers.3.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="650" name="Constant_18469" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="33583099" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="651" name="__module.model.model.decoder.layers.3.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="652" name="Constant_18470" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="33585147" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="653" name="__module.model.model.decoder.layers.3.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="443,hidden_states.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="654" name="Constant_18216" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="33587195" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="655" name="Convert_24283" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="656" name="Constant_18216/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="33718267" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="657" name="Convert_24285" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="658" name="Constant_18216/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="659" name="Constant_18216/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="33719291" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="660" name="Constant_18216/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="661" name="Constant_24290" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="662" name="Reshape_24291" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="663" name="Constant_18216/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="664" name="Multiply_18173" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="665" name="Constant_18471" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="33723387" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="666" name="__module.model.model.decoder.layers.3.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="453,tensor.37">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="667" name="Constant_18853" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="668" name="__module.model.model.decoder.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="455">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="669" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="670" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="456">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="671" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="33725435" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="672" name="Convert_24272" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="673" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="33856507" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="674" name="Convert_24274" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="675" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="676" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="33857531" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="677" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="678" name="Constant_24279" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="679" name="Reshape_24280" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="680" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="681" name="__module.model.model.decoder.layers.3.self_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="459,tensor.39">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="682" name="Constant_18854" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="683" name="__module.model.model.decoder.layers.3.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>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="461">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="684" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="685" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="462">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="686" name="__module.model.model.decoder.layers.3.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="472,attn_weights.7">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="687" name="__module.model.model.decoder.layers.3.self_attn/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="478,input.51">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="688" name="__module.model.model.decoder.layers.3.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="479,input.53">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="689" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="33861627" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="690" name="Convert_24261" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="691" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="33992699" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="692" name="Convert_24263" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="693" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="694" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="33993723" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="695" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="696" name="Constant_24268" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="697" name="Reshape_24269" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="698" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="699" name="__module.model.model.decoder.layers.3.self_attn.v_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="700" name="Constant_18472" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="33997819" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="701" name="__module.model.model.decoder.layers.3.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="466,tensor.41">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="702" name="Constant_18855" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="703" name="__module.model.model.decoder.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="468">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="704" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="705" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="469">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="706" name="__module.model.model.decoder.layers.3.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="481,attn_output.25">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="707" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="708" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="482,attn_output.27">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="709" name="Constant_18856" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27358099" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="710" name="__module.model.model.decoder.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="484">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="711" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="33999867" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="712" name="Convert_24294" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="713" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="34130939" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="714" name="Convert_24296" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="715" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="716" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="34131963" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="717" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="718" name="Constant_24301" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="719" name="Reshape_24302" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="720" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="721" name="__module.model.model.decoder.layers.3.self_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="722" name="Constant_18473" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34136059" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="723" name="__module.model.model.decoder.layers.3.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="487,input.55">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="724" name="__module.model.model.decoder.layers.3/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="489,residual.21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="725" name="__module.model.model.decoder.layers.3.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="726" name="__module.model.model.decoder.layers.3.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>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="727" name="Constant_18474" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34138107" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="728" name="__module.model.model.decoder.layers.3.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="729" name="Constant_18475" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34140155" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="730" name="__module.model.model.decoder.layers.3.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="493,hidden_states.35">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="731" name="Constant_18219" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="34142203" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="732" name="Convert_24305" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="733" name="Constant_18219/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="34273275" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="734" name="Convert_24307" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="735" name="Constant_18219/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="736" name="Constant_18219/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="34274299" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="737" name="Constant_18219/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="738" name="Constant_24312" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="739" name="Reshape_24313" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="740" name="Constant_18219/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="741" name="Multiply_18177" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="742" name="Constant_18476" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34278395" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="743" name="__module.model.model.decoder.layers.3.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="503,tensor.43">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="744" name="Constant_18857" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="745" name="__module.model.model.decoder.layers.3.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="505">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="746" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="747" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="506">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="748" name="self.model.model.decoder.layers.3.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="34280443" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="749" name="Convert_23986" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="750" name="self.model.model.decoder.layers.3.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="34411515" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="751" name="Convert_23988" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="752" name="self.model.model.decoder.layers.3.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="753" name="self.model.model.decoder.layers.3.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="34412539" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="754" name="self.model.model.decoder.layers.3.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="755" name="Constant_23993" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="756" name="Reshape_23994" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="757" name="self.model.model.decoder.layers.3.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="758" name="__module.model.model.decoder.layers.3.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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="509,tensor.45">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="759" name="__module.model.model.decoder.layers.3.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="511">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="760" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="761" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="512">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="762" name="__module.model.model.decoder.layers.3.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="522,input.57">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="763" name="__module.model.model.decoder.layers.3.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="523,input.59">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="764" name="self.model.model.decoder.layers.3.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="34416635" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="765" name="Convert_23975" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="766" name="self.model.model.decoder.layers.3.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="34547707" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="767" name="Convert_23977" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="768" name="self.model.model.decoder.layers.3.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="769" name="self.model.model.decoder.layers.3.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="34548731" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="770" name="self.model.model.decoder.layers.3.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="771" name="Constant_23982" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="772" name="Reshape_23983" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="773" name="self.model.model.decoder.layers.3.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="774" name="__module.model.model.decoder.layers.3.encoder_attn.v_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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="775" name="Constant_18477" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34552827" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="776" name="__module.model.model.decoder.layers.3.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="516,tensor.47">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="777" name="__module.model.model.decoder.layers.3.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="518">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="778" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="779" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="519">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="780" name="__module.model.model.decoder.layers.3.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="525,attn_output.29">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="781" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="782" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="526,attn_output.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="783" name="Constant_18858" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27913155" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="784" name="__module.model.model.decoder.layers.3.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="528">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="785" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="34554875" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="786" name="Convert_24316" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="787" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="34685947" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="788" name="Convert_24318" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="789" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="790" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="34686971" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="791" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="792" name="Constant_24323" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="793" name="Reshape_24324" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="794" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="795" name="__module.model.model.decoder.layers.3.encoder_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="796" name="Constant_18478" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34691067" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="797" name="__module.model.model.decoder.layers.3.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="531,input.61">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="798" name="__module.model.model.decoder.layers.3/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="533,residual.23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="799" name="__module.model.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="800" name="__module.model.model.decoder.layers.3.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="801" name="Constant_18479" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34693115" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="802" name="__module.model.model.decoder.layers.3.final_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="803" name="Constant_18480" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="34695163" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="804" name="__module.model.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="537">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="805" name="self.model.model.decoder.layers.3.fc1.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 128" offset="34697211" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="806" name="Convert_23865" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="807" name="self.model.model.decoder.layers.3.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 1" offset="35221499" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="808" name="Convert_23867" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="809" name="self.model.model.decoder.layers.3.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="810" name="self.model.model.decoder.layers.3.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 4, 1" offset="35225595" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="811" name="self.model.model.decoder.layers.3.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="812" name="Constant_23872" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="28600283" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="813" name="Reshape_23873" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="814" name="self.model.model.decoder.layers.3.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="815" name="__module.model.model.decoder.layers.3.fc1/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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="816" name="Constant_18481" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 2048" offset="35241979" size="8192" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="817" name="__module.model.model.decoder.layers.3.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="540">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="818" name="__module.model.model.decoder.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="541,input.63">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="819" name="self.model.model.decoder.layers.3.fc2.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 128" offset="35250171" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="820" name="Convert_23876" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="821" name="self.model.model.decoder.layers.3.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 1" offset="35774459" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="822" name="Convert_23878" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="823" name="self.model.model.decoder.layers.3.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="824" name="self.model.model.decoder.layers.3.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 16, 1" offset="35778555" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="825" name="self.model.model.decoder.layers.3.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="826" name="Constant_23883" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="29153259" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="827" name="Reshape_23884" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="828" name="self.model.model.decoder.layers.3.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="829" name="__module.model.model.decoder.layers.3.fc2/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>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="830" name="Constant_18482" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="35794939" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="831" name="__module.model.model.decoder.layers.3.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="545,input.65">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="832" name="__module.model.model.decoder.layers.3/aten::add/Add_2" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="547,residual.25">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="833" name="__module.model.model.decoder.layers.4.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="834" name="__module.model.model.decoder.layers.4.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="835" name="Constant_18483" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="35796987" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="836" name="__module.model.model.decoder.layers.4.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="837" name="Constant_18484" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="35799035" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="838" name="__module.model.model.decoder.layers.4.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="558,hidden_states.41">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="839" name="Constant_18222" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="35801083" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="840" name="Convert_24349" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="841" name="Constant_18222/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="35932155" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="842" name="Convert_24351" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="843" name="Constant_18222/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="844" name="Constant_18222/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="35933179" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="845" name="Constant_18222/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="846" name="Constant_24356" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="847" name="Reshape_24357" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="848" name="Constant_18222/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="849" name="Multiply_18181" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="850" name="Constant_18485" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="35937275" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="851" name="__module.model.model.decoder.layers.4.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="568,tensor.49">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="852" name="Constant_18859" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="853" name="__module.model.model.decoder.layers.4.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="570">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="854" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="855" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="571">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="856" name="self.model.model.decoder.layers.4.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="35939323" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="857" name="Convert_24338" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="858" name="self.model.model.decoder.layers.4.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36070395" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="859" name="Convert_24340" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="860" name="self.model.model.decoder.layers.4.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="861" name="self.model.model.decoder.layers.4.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36071419" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="862" name="self.model.model.decoder.layers.4.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="863" name="Constant_24345" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="864" name="Reshape_24346" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="865" name="self.model.model.decoder.layers.4.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="866" name="__module.model.model.decoder.layers.4.self_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="574,tensor.51">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="867" name="Constant_18860" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="868" name="__module.model.model.decoder.layers.4.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>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="576">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="869" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="870" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="577">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="871" name="__module.model.model.decoder.layers.4.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="587,attn_weights.9">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="872" name="__module.model.model.decoder.layers.4.self_attn/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="593,input.67">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="873" name="__module.model.model.decoder.layers.4.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="594,input.69">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="874" name="self.model.model.decoder.layers.4.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="36075515" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="875" name="Convert_24327" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="876" name="self.model.model.decoder.layers.4.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36206587" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="877" name="Convert_24329" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="878" name="self.model.model.decoder.layers.4.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="879" name="self.model.model.decoder.layers.4.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36207611" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="880" name="self.model.model.decoder.layers.4.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="881" name="Constant_24334" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="882" name="Reshape_24335" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="883" name="self.model.model.decoder.layers.4.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="884" name="__module.model.model.decoder.layers.4.self_attn.v_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="885" name="Constant_18486" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36211707" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="886" name="__module.model.model.decoder.layers.4.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="581,tensor.53">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="887" name="Constant_18861" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="888" name="__module.model.model.decoder.layers.4.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="583">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="889" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="890" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="584">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="891" name="__module.model.model.decoder.layers.4.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="596,attn_output.33">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="892" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="893" name="__module.model.model.decoder.layers.4.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="597,attn_output.35">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="894" name="Constant_18862" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27358099" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="895" name="__module.model.model.decoder.layers.4.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="599">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="896" name="self.model.model.decoder.layers.4.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="36213755" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="897" name="Convert_24360" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="898" name="self.model.model.decoder.layers.4.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36344827" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="899" name="Convert_24362" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="900" name="self.model.model.decoder.layers.4.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="901" name="self.model.model.decoder.layers.4.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36345851" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="902" name="self.model.model.decoder.layers.4.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="903" name="Constant_24367" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="904" name="Reshape_24368" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="905" name="self.model.model.decoder.layers.4.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="906" name="__module.model.model.decoder.layers.4.self_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="907" name="Constant_18487" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36349947" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="908" name="__module.model.model.decoder.layers.4.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="602,input.71">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="909" name="__module.model.model.decoder.layers.4/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="604,residual.27">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="910" name="__module.model.model.decoder.layers.4.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="911" name="__module.model.model.decoder.layers.4.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>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="912" name="Constant_18488" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36351995" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="913" name="__module.model.model.decoder.layers.4.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="914" name="Constant_18489" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36354043" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="915" name="__module.model.model.decoder.layers.4.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="608,hidden_states.45">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="916" name="Constant_18225" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="36356091" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="917" name="Convert_24371" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="918" name="Constant_18225/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36487163" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="919" name="Convert_24373" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="920" name="Constant_18225/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="921" name="Constant_18225/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36488187" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="922" name="Constant_18225/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="923" name="Constant_24378" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="924" name="Reshape_24379" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="925" name="Constant_18225/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="926" name="Multiply_18185" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="927" name="Constant_18490" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36492283" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="928" name="__module.model.model.decoder.layers.4.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="618,tensor.55">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="929" name="Constant_18863" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="930" name="__module.model.model.decoder.layers.4.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="620">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="931" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="932" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="621">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="933" name="self.model.model.decoder.layers.4.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="36494331" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="934" name="Convert_23964" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="935" name="self.model.model.decoder.layers.4.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36625403" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="936" name="Convert_23966" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="937" name="self.model.model.decoder.layers.4.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="938" name="self.model.model.decoder.layers.4.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36626427" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="939" name="self.model.model.decoder.layers.4.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="940" name="Constant_23971" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="941" name="Reshape_23972" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="942" name="self.model.model.decoder.layers.4.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="943" name="__module.model.model.decoder.layers.4.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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="624,tensor.57">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="944" name="__module.model.model.decoder.layers.4.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="626">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="945" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="946" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="627">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="947" name="__module.model.model.decoder.layers.4.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="637,input.73">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="948" name="__module.model.model.decoder.layers.4.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="638,input.75">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="949" name="self.model.model.decoder.layers.4.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="36630523" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="950" name="Convert_23953" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="951" name="self.model.model.decoder.layers.4.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36761595" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="952" name="Convert_23955" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="953" name="self.model.model.decoder.layers.4.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="954" name="self.model.model.decoder.layers.4.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36762619" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="955" name="self.model.model.decoder.layers.4.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="956" name="Constant_23960" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="957" name="Reshape_23961" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="958" name="self.model.model.decoder.layers.4.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="959" name="__module.model.model.decoder.layers.4.encoder_attn.v_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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="960" name="Constant_18491" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36766715" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="961" name="__module.model.model.decoder.layers.4.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="631,tensor.59">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="962" name="__module.model.model.decoder.layers.4.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="633">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="963" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="964" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="634">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="965" name="__module.model.model.decoder.layers.4.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="640,attn_output.37">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="966" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="967" name="__module.model.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="641,attn_output.39">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="968" name="Constant_18864" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27913155" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="969" name="__module.model.model.decoder.layers.4.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="643">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="970" name="self.model.model.decoder.layers.4.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="36768763" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="971" name="Convert_24382" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="972" name="self.model.model.decoder.layers.4.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="36899835" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="973" name="Convert_24384" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="974" name="self.model.model.decoder.layers.4.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="975" name="self.model.model.decoder.layers.4.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="36900859" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="976" name="self.model.model.decoder.layers.4.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="977" name="Constant_24389" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="978" name="Reshape_24390" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="979" name="self.model.model.decoder.layers.4.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="980" name="__module.model.model.decoder.layers.4.encoder_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="981" name="Constant_18492" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36904955" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="982" name="__module.model.model.decoder.layers.4.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="646,input.77">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="983" name="__module.model.model.decoder.layers.4/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="648,residual.29">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="984" name="__module.model.model.decoder.layers.4.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="985" name="__module.model.model.decoder.layers.4.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="986" name="Constant_18493" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36907003" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="987" name="__module.model.model.decoder.layers.4.final_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="988" name="Constant_18494" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="36909051" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="989" name="__module.model.model.decoder.layers.4.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="652">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="990" name="self.model.model.decoder.layers.4.fc1.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 128" offset="36911099" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="991" name="Convert_23887" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="992" name="self.model.model.decoder.layers.4.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 1" offset="37435387" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="993" name="Convert_23889" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="994" name="self.model.model.decoder.layers.4.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="995" name="self.model.model.decoder.layers.4.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 4, 1" offset="37439483" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="996" name="self.model.model.decoder.layers.4.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="997" name="Constant_23894" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="28600283" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="998" name="Reshape_23895" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="999" name="self.model.model.decoder.layers.4.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1000" name="__module.model.model.decoder.layers.4.fc1/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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1001" name="Constant_18495" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 2048" offset="37455867" size="8192" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1002" name="__module.model.model.decoder.layers.4.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="655">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1003" name="__module.model.model.decoder.layers.4.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="656,input.79">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1004" name="self.model.model.decoder.layers.4.fc2.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 128" offset="37464059" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1005" name="Convert_23898" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1006" name="self.model.model.decoder.layers.4.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 1" offset="37988347" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1007" name="Convert_23900" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1008" name="self.model.model.decoder.layers.4.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1009" name="self.model.model.decoder.layers.4.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 16, 1" offset="37992443" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1010" name="self.model.model.decoder.layers.4.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1011" name="Constant_23905" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="29153259" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1012" name="Reshape_23906" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1013" name="self.model.model.decoder.layers.4.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1014" name="__module.model.model.decoder.layers.4.fc2/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>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1015" name="Constant_18496" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38008827" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1016" name="__module.model.model.decoder.layers.4.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="660,input.81">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1017" name="__module.model.model.decoder.layers.4/aten::add/Add_2" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="662,residual.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1018" name="__module.model.model.decoder.layers.5.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1019" name="__module.model.model.decoder.layers.5.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1020" name="Constant_18497" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38010875" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1021" name="__module.model.model.decoder.layers.5.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1022" name="Constant_18498" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38012923" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1023" name="__module.model.model.decoder.layers.5.self_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="673,hidden_states.51">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1024" name="Constant_18228" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38014971" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1025" name="Convert_24415" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1026" name="Constant_18228/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38146043" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1027" name="Convert_24417" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1028" name="Constant_18228/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1029" name="Constant_18228/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38147067" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1030" name="Constant_18228/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1031" name="Constant_24422" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1032" name="Reshape_24423" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1033" name="Constant_18228/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1034" name="Multiply_18189" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1035" name="Constant_18499" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38151163" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1036" name="__module.model.model.decoder.layers.5.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="683,tensor.61">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1037" name="Constant_18865" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1038" name="__module.model.model.decoder.layers.5.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="685">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1039" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1040" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="686">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1041" name="self.model.model.decoder.layers.5.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38153211" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1042" name="Convert_24404" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1043" name="self.model.model.decoder.layers.5.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38284283" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1044" name="Convert_24406" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1045" name="self.model.model.decoder.layers.5.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1046" name="self.model.model.decoder.layers.5.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38285307" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1047" name="self.model.model.decoder.layers.5.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1048" name="Constant_24411" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1049" name="Reshape_24412" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1050" name="self.model.model.decoder.layers.5.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1051" name="__module.model.model.decoder.layers.5.self_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="689,tensor.63">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1052" name="Constant_18866" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1053" name="__module.model.model.decoder.layers.5.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>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="691">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1054" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1055" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="692">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1056" name="__module.model.model.decoder.layers.5.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="702,attn_weights">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1057" name="__module.model.model.decoder.layers.5.self_attn/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="708,input.83">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1058" name="__module.model.model.decoder.layers.5.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="709,input.85">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1059" name="self.model.model.decoder.layers.5.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38289403" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1060" name="Convert_24393" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1061" name="self.model.model.decoder.layers.5.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38420475" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1062" name="Convert_24395" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1063" name="self.model.model.decoder.layers.5.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1064" name="self.model.model.decoder.layers.5.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38421499" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1065" name="self.model.model.decoder.layers.5.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1066" name="Constant_24400" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1067" name="Reshape_24401" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1068" name="self.model.model.decoder.layers.5.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1069" name="__module.model.model.decoder.layers.5.self_attn.v_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1070" name="Constant_18500" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38425595" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1071" name="__module.model.model.decoder.layers.5.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="696,tensor.65">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1072" name="Constant_18867" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1073" name="__module.model.model.decoder.layers.5.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="698">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1074" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1075" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="699">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1076" name="__module.model.model.decoder.layers.5.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="711,attn_output.41">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1077" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1078" name="__module.model.model.decoder.layers.5.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="712,attn_output.43">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1079" name="Constant_18868" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27358099" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1080" name="__module.model.model.decoder.layers.5.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="714">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1081" name="self.model.model.decoder.layers.5.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38427643" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1082" name="Convert_24426" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1083" name="self.model.model.decoder.layers.5.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38558715" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1084" name="Convert_24428" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1085" name="self.model.model.decoder.layers.5.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1086" name="self.model.model.decoder.layers.5.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38559739" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1087" name="self.model.model.decoder.layers.5.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1088" name="Constant_24433" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1089" name="Reshape_24434" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1090" name="self.model.model.decoder.layers.5.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1091" name="__module.model.model.decoder.layers.5.self_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1092" name="Constant_18501" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38563835" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1093" name="__module.model.model.decoder.layers.5.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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="717,input.87">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1094" name="__module.model.model.decoder.layers.5/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="719,residual.33">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1095" name="__module.model.model.decoder.layers.5.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1096" name="__module.model.model.decoder.layers.5.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>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1097" name="Constant_18502" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38565883" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1098" name="__module.model.model.decoder.layers.5.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1099" name="Constant_18503" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38567931" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1100" name="__module.model.model.decoder.layers.5.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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="723,hidden_states.55">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1101" name="Constant_18231" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38569979" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1102" name="Convert_24437" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1103" name="Constant_18231/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38701051" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1104" name="Convert_24439" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1105" name="Constant_18231/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1106" name="Constant_18231/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38702075" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1107" name="Constant_18231/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1108" name="Constant_24444" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1109" name="Reshape_24445" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1110" name="Constant_18231/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1111" name="Multiply_18193" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1112" name="Constant_18504" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38706171" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1113" name="__module.model.model.decoder.layers.5.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="733,tensor.67">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1114" name="Constant_18869" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="27083591" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1115" name="__module.model.model.decoder.layers.5.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="735">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1116" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1117" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="736">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1118" name="self.model.model.decoder.layers.5.encoder_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38708219" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1119" name="Convert_23942" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1120" name="self.model.model.decoder.layers.5.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38839291" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1121" name="Convert_23944" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1122" name="self.model.model.decoder.layers.5.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1123" name="self.model.model.decoder.layers.5.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38840315" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1124" name="self.model.model.decoder.layers.5.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1125" name="Constant_23949" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1126" name="Reshape_23950" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1127" name="self.model.model.decoder.layers.5.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1128" name="__module.model.model.decoder.layers.5.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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="739,tensor.69">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1129" name="__module.model.model.decoder.layers.5.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="741">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1130" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1131" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="742">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1132" name="__module.model.model.decoder.layers.5.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="752,input.89">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1133" name="__module.model.model.decoder.layers.5.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="753,input.91">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1134" name="self.model.model.decoder.layers.5.encoder_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38844411" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1135" name="Convert_23931" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1136" name="self.model.model.decoder.layers.5.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="38975483" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1137" name="Convert_23933" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1138" name="self.model.model.decoder.layers.5.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1139" name="self.model.model.decoder.layers.5.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="38976507" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1140" name="self.model.model.decoder.layers.5.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1141" name="Constant_23938" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1142" name="Reshape_23939" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1143" name="self.model.model.decoder.layers.5.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1144" name="__module.model.model.decoder.layers.5.encoder_attn.v_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>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1145" name="Constant_18505" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="38980603" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1146" name="__module.model.model.decoder.layers.5.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="746,tensor">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1147" name="__module.model.model.decoder.layers.5.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="748">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1148" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1149" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="749">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1150" name="__module.model.model.decoder.layers.5.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>8</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="755,attn_output.45">
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>-1</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1151" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="27083623" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1152" name="__module.model.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>8</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="756,attn_output">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1153" name="Constant_18870" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="27913155" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1154" name="__module.model.model.decoder.layers.5.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="758">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1155" name="self.model.model.decoder.layers.5.encoder_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 128" offset="38982651" size="131072" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1156" name="Convert_24448" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1157" name="self.model.model.decoder.layers.5.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 4, 1" offset="39113723" size="1024" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1158" name="Convert_24450" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1159" name="self.model.model.decoder.layers.5.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1160" name="self.model.model.decoder.layers.5.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 4, 1" offset="39114747" size="4096" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1161" name="self.model.model.decoder.layers.5.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1162" name="Constant_24455" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="27081527" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1163" name="Reshape_24456" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1164" name="self.model.model.decoder.layers.5.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1165" name="__module.model.model.decoder.layers.5.encoder_attn.out_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1166" name="Constant_18506" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="39118843" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1167" name="__module.model.model.decoder.layers.5.encoder_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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="761,input.93">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1168" name="__module.model.model.decoder.layers.5/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="763,residual">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1169" name="__module.model.model.decoder.layers.5.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1170" name="__module.model.model.decoder.layers.5.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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1171" name="Constant_18507" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="39120891" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1172" name="__module.model.model.decoder.layers.5.final_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>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1173" name="Constant_18508" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="39122939" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1174" name="__module.model.model.decoder.layers.5.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="767">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1175" name="self.model.model.decoder.layers.5.fc1.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 128" offset="39124987" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1176" name="Convert_23909" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1177" name="self.model.model.decoder.layers.5.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="2048, 4, 1" offset="39649275" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1178" name="Convert_23911" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1179" name="self.model.model.decoder.layers.5.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1180" name="self.model.model.decoder.layers.5.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 4, 1" offset="39653371" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1181" name="self.model.model.decoder.layers.5.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1182" name="Constant_23916" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="28600283" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1183" name="Reshape_23917" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>4</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1184" name="self.model.model.decoder.layers.5.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1185" name="__module.model.model.decoder.layers.5.fc1/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>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1186" name="Constant_18509" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 2048" offset="39669755" size="8192" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1187" name="__module.model.model.decoder.layers.5.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="770">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1188" name="__module.model.model.decoder.layers.5.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="771,input.95">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1189" name="self.model.model.decoder.layers.5.fc2.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 128" offset="39677947" size="524288" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1190" name="Convert_23920" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1191" name="self.model.model.decoder.layers.5.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="512, 16, 1" offset="40202235" size="4096" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1192" name="Convert_23922" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1193" name="self.model.model.decoder.layers.5.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1194" name="self.model.model.decoder.layers.5.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 16, 1" offset="40206331" size="16384" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1195" name="self.model.model.decoder.layers.5.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1196" name="Constant_23927" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="29153259" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1197" name="Reshape_23928" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>16</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1198" name="self.model.model.decoder.layers.5.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1199" name="__module.model.model.decoder.layers.5.fc2/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>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1200" name="Constant_18510" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="40222715" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1201" name="__module.model.model.decoder.layers.5.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="775,input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1202" name="__module.model.model.decoder.layers.5/aten::add/Add_2" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="777">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1203" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="26941235" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1204" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</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>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1205" name="Constant_18511" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="40224763" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1206" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1207" name="Constant_18512" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="40226811" size="2048" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1208" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="781">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1209" 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">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>51865</dim>
+					<dim>512</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="logits">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>51865</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1210" name="Result_12155" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>51865</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="959" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="758" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="774" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="943" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="199" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="219" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="388" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="404" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="573" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="589" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="1144" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="1128" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="11" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="24" 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="6" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
+		<edge from-layer="6" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="1209" to-port="1" />
+		<edge from-layer="9" from-port="1" to-layer="14" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="12" to-port="0" />
+		<edge from-layer="12" from-port="1" to-layer="14" to-port="1" />
+		<edge from-layer="13" from-port="0" to-layer="14" to-port="2" />
+		<edge from-layer="14" from-port="3" to-layer="34" to-port="0" />
+		<edge from-layer="15" from-port="0" to-layer="16" to-port="0" />
+		<edge from-layer="16" from-port="1" to-layer="19" to-port="0" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
+		<edge from-layer="18" from-port="1" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="21" to-port="0" />
+		<edge from-layer="20" from-port="0" to-layer="21" to-port="1" />
+		<edge from-layer="21" from-port="2" to-layer="22" to-port="0" />
+		<edge from-layer="22" from-port="1" to-layer="33" to-port="0" />
+		<edge from-layer="23" from-port="0" to-layer="30" to-port="1" />
+		<edge from-layer="23" from-port="0" to-layer="109" to-port="1" />
+		<edge from-layer="23" from-port="0" to-layer="29" to-port="0" />
+		<edge from-layer="24" from-port="1" to-layer="114" to-port="0" />
+		<edge from-layer="24" from-port="1" to-layer="27" to-port="0" />
+		<edge from-layer="25" from-port="0" to-layer="27" to-port="1" />
+		<edge from-layer="26" from-port="0" to-layer="27" to-port="2" />
+		<edge from-layer="27" from-port="3" to-layer="92" to-port="0" />
+		<edge from-layer="27" from-port="3" to-layer="79" to-port="0" />
+		<edge from-layer="27" from-port="3" to-layer="77" to-port="0" />
+		<edge from-layer="27" from-port="3" to-layer="29" to-port="1" />
+		<edge from-layer="28" from-port="0" to-layer="29" to-port="2" />
+		<edge from-layer="29" from-port="3" to-layer="30" to-port="0" />
+		<edge from-layer="29" from-port="3" to-layer="105" to-port="0" />
+		<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="34" to-port="1" />
+		<edge from-layer="34" from-port="2" to-layer="165" to-port="0" />
+		<edge from-layer="34" from-port="2" to-layer="36" to-port="0" />
+		<edge from-layer="35" from-port="0" to-layer="36" to-port="1" />
+		<edge from-layer="36" from-port="2" to-layer="38" to-port="0" />
+		<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
+		<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
+		<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
+		<edge from-layer="40" from-port="2" to-layer="121" to-port="0" />
+		<edge from-layer="40" from-port="2" to-layer="140" to-port="0" />
+		<edge from-layer="40" from-port="2" to-layer="68" to-port="0" />
+		<edge from-layer="40" from-port="2" to-layer="51" to-port="0" />
+		<edge from-layer="41" from-port="0" to-layer="42" to-port="0" />
+		<edge from-layer="42" from-port="1" to-layer="45" to-port="0" />
+		<edge from-layer="43" from-port="0" to-layer="44" to-port="0" />
+		<edge from-layer="44" from-port="1" to-layer="45" to-port="1" />
+		<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
+		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
+		<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
+		<edge from-layer="48" from-port="0" 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="51" to-port="1" />
+		<edge from-layer="51" from-port="2" to-layer="53" to-port="0" />
+		<edge from-layer="52" from-port="0" to-layer="53" to-port="1" />
+		<edge from-layer="53" from-port="2" to-layer="55" 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="57" to-port="0" />
+		<edge from-layer="56" from-port="0" to-layer="57" to-port="1" />
+		<edge from-layer="57" from-port="2" to-layer="73" 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="62" to-port="0" />
+		<edge from-layer="60" from-port="0" to-layer="61" to-port="0" />
+		<edge from-layer="61" from-port="1" 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="66" to-port="0" />
+		<edge from-layer="65" from-port="0" to-layer="66" to-port="1" />
+		<edge from-layer="66" from-port="2" to-layer="67" to-port="0" />
+		<edge from-layer="67" from-port="1" to-layer="68" to-port="1" />
+		<edge from-layer="68" from-port="2" to-layer="70" to-port="0" />
+		<edge from-layer="69" from-port="0" to-layer="70" to-port="1" />
+		<edge from-layer="70" from-port="2" to-layer="72" to-port="0" />
+		<edge from-layer="71" from-port="0" to-layer="72" to-port="1" />
+		<edge from-layer="72" from-port="2" to-layer="73" to-port="1" />
+		<edge from-layer="73" from-port="2" to-layer="128" to-port="0" />
+		<edge from-layer="74" from-port="0" to-layer="90" to-port="1" />
+		<edge from-layer="74" from-port="0" to-layer="89" to-port="0" />
+		<edge from-layer="75" from-port="0" to-layer="83" to-port="0" />
+		<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
+		<edge from-layer="77" from-port="2" to-layer="82" to-port="0" />
+		<edge from-layer="78" from-port="0" to-layer="79" to-port="1" />
+		<edge from-layer="79" from-port="2" to-layer="81" to-port="0" />
+		<edge from-layer="79" from-port="2" to-layer="101" to-port="1" />
+		<edge from-layer="80" from-port="0" 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="1" />
+		<edge from-layer="83" from-port="2" to-layer="98" to-port="1" />
+		<edge from-layer="83" from-port="2" to-layer="84" to-port="0" />
+		<edge from-layer="84" from-port="1" to-layer="87" to-port="0" />
+		<edge from-layer="85" from-port="0" to-layer="87" to-port="1" />
+		<edge from-layer="86" from-port="0" to-layer="87" to-port="2" />
+		<edge from-layer="87" from-port="3" to-layer="89" to-port="1" />
+		<edge from-layer="88" from-port="0" to-layer="95" to-port="1" />
+		<edge from-layer="88" from-port="0" to-layer="94" to-port="2" />
+		<edge from-layer="88" from-port="0" to-layer="89" to-port="2" />
+		<edge from-layer="89" from-port="3" to-layer="90" to-port="0" />
+		<edge from-layer="90" from-port="2" to-layer="96" to-port="0" />
+		<edge from-layer="91" from-port="0" to-layer="94" to-port="0" />
+		<edge from-layer="91" from-port="0" to-layer="93" to-port="1" />
+		<edge from-layer="92" from-port="1" to-layer="93" to-port="0" />
+		<edge from-layer="93" from-port="2" to-layer="94" to-port="1" />
+		<edge from-layer="94" from-port="3" to-layer="95" to-port="0" />
+		<edge from-layer="95" from-port="2" to-layer="96" to-port="1" />
+		<edge from-layer="96" from-port="2" to-layer="98" to-port="0" />
+		<edge from-layer="97" from-port="0" 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="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="119" to-port="0" />
+		<edge from-layer="112" from-port="0" to-layer="114" to-port="1" />
+		<edge from-layer="113" from-port="0" to-layer="114" to-port="2" />
+		<edge from-layer="114" from-port="3" to-layer="118" to-port="0" />
+		<edge from-layer="114" from-port="3" to-layer="203" to-port="0" />
+		<edge from-layer="115" from-port="0" to-layer="118" to-port="1" />
+		<edge from-layer="116" from-port="0" to-layer="118" to-port="2" />
+		<edge from-layer="117" from-port="0" to-layer="118" to-port="3" />
+		<edge from-layer="118" from-port="4" to-layer="119" to-port="1" />
+		<edge from-layer="119" from-port="2" to-layer="127" to-port="0" />
+		<edge from-layer="120" from-port="0" to-layer="127" to-port="1" />
+		<edge from-layer="121" from-port="1" to-layer="124" to-port="0" />
+		<edge from-layer="122" from-port="0" to-layer="124" to-port="1" />
+		<edge from-layer="123" from-port="0" to-layer="124" to-port="2" />
+		<edge from-layer="124" from-port="3" to-layer="127" to-port="2" />
+		<edge from-layer="125" from-port="0" to-layer="127" to-port="3" />
+		<edge from-layer="126" from-port="0" to-layer="127" to-port="4" />
+		<edge from-layer="127" from-port="5" to-layer="687" to-port="1" />
+		<edge from-layer="127" from-port="5" to-layer="317" to-port="1" />
+		<edge from-layer="127" from-port="5" to-layer="502" to-port="1" />
+		<edge from-layer="127" from-port="5" to-layer="1057" to-port="1" />
+		<edge from-layer="127" from-port="5" to-layer="872" to-port="1" />
+		<edge from-layer="127" from-port="5" to-layer="128" to-port="1" />
+		<edge from-layer="128" from-port="2" to-layer="129" to-port="0" />
+		<edge from-layer="129" from-port="1" to-layer="147" 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="134" to-port="0" />
+		<edge from-layer="132" from-port="0" to-layer="133" to-port="0" />
+		<edge from-layer="133" from-port="1" 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="138" to-port="0" />
+		<edge from-layer="137" from-port="0" 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="142" to-port="0" />
+		<edge from-layer="141" from-port="0" to-layer="142" to-port="1" />
+		<edge from-layer="142" from-port="2" to-layer="144" to-port="0" />
+		<edge from-layer="143" from-port="0" to-layer="144" to-port="1" />
+		<edge from-layer="144" from-port="2" to-layer="146" to-port="0" />
+		<edge from-layer="145" from-port="0" 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="149" to-port="0" />
+		<edge from-layer="148" from-port="0" to-layer="149" to-port="1" />
+		<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="162" to-port="0" />
+		<edge from-layer="152" from-port="0" to-layer="153" to-port="0" />
+		<edge from-layer="153" from-port="1" 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="158" to-port="0" />
+		<edge from-layer="157" from-port="0" to-layer="158" to-port="1" />
+		<edge from-layer="158" from-port="2" to-layer="160" to-port="0" />
+		<edge from-layer="159" from-port="0" to-layer="160" to-port="1" />
+		<edge from-layer="160" from-port="2" 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="165" to-port="1" />
+		<edge from-layer="165" from-port="2" to-layer="243" to-port="0" />
+		<edge from-layer="165" from-port="2" to-layer="167" to-port="0" />
+		<edge from-layer="166" from-port="0" to-layer="167" to-port="1" />
+		<edge from-layer="167" from-port="2" to-layer="169" to-port="0" />
+		<edge from-layer="168" from-port="0" to-layer="169" to-port="1" />
+		<edge from-layer="169" from-port="2" to-layer="171" to-port="0" />
+		<edge from-layer="170" from-port="0" to-layer="171" to-port="1" />
+		<edge from-layer="171" from-port="2" to-layer="182" to-port="0" />
+		<edge from-layer="172" from-port="0" to-layer="173" to-port="0" />
+		<edge from-layer="173" from-port="1" to-layer="176" to-port="0" />
+		<edge from-layer="174" from-port="0" to-layer="175" to-port="0" />
+		<edge from-layer="175" from-port="1" to-layer="176" to-port="1" />
+		<edge from-layer="176" from-port="2" to-layer="178" to-port="0" />
+		<edge from-layer="177" from-port="0" to-layer="178" to-port="1" />
+		<edge from-layer="178" from-port="2" to-layer="180" to-port="0" />
+		<edge from-layer="179" from-port="0" to-layer="180" to-port="1" />
+		<edge from-layer="180" from-port="2" to-layer="181" to-port="0" />
+		<edge from-layer="181" from-port="1" to-layer="182" to-port="1" />
+		<edge from-layer="182" from-port="2" to-layer="184" to-port="0" />
+		<edge from-layer="183" from-port="0" 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="207" 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="193" to-port="0" />
+		<edge from-layer="191" from-port="0" to-layer="192" to-port="0" />
+		<edge from-layer="192" from-port="1" to-layer="193" to-port="1" />
+		<edge from-layer="193" from-port="2" to-layer="195" to-port="0" />
+		<edge from-layer="194" from-port="0" to-layer="195" to-port="1" />
+		<edge from-layer="195" from-port="2" to-layer="197" 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="198" to-port="0" />
+		<edge from-layer="198" from-port="1" to-layer="199" to-port="1" />
+		<edge from-layer="199" from-port="2" to-layer="204" to-port="0" />
+		<edge from-layer="200" from-port="0" to-layer="203" to-port="1" />
+		<edge from-layer="201" from-port="0" to-layer="203" to-port="2" />
+		<edge from-layer="202" from-port="0" to-layer="203" to-port="3" />
+		<edge from-layer="203" from-port="4" to-layer="1129" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="204" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="1147" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="592" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="574" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="407" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="759" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="222" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="389" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="777" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="944" to-port="1" />
+		<edge from-layer="203" from-port="4" to-layer="962" to-port="1" />
+		<edge from-layer="204" from-port="2" to-layer="206" to-port="0" />
+		<edge from-layer="205" from-port="0" to-layer="206" to-port="1" />
+		<edge from-layer="206" from-port="2" 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="225" to-port="0" />
+		<edge from-layer="209" from-port="0" 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="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="218" to-port="0" />
+		<edge from-layer="218" from-port="1" to-layer="219" to-port="1" />
+		<edge from-layer="219" from-port="2" to-layer="221" 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="222" to-port="0" />
+		<edge from-layer="222" from-port="2" to-layer="224" to-port="0" />
+		<edge from-layer="223" from-port="0" to-layer="224" to-port="1" />
+		<edge from-layer="224" from-port="2" 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="229" to-port="0" />
+		<edge from-layer="228" from-port="0" to-layer="229" to-port="1" />
+		<edge from-layer="229" from-port="2" to-layer="240" to-port="0" />
+		<edge from-layer="230" from-port="0" to-layer="231" to-port="0" />
+		<edge from-layer="231" from-port="1" to-layer="234" to-port="0" />
+		<edge from-layer="232" from-port="0" to-layer="233" to-port="0" />
+		<edge from-layer="233" from-port="1" to-layer="234" to-port="1" />
+		<edge from-layer="234" from-port="2" to-layer="236" to-port="0" />
+		<edge from-layer="235" from-port="0" to-layer="236" to-port="1" />
+		<edge from-layer="236" from-port="2" to-layer="238" to-port="0" />
+		<edge from-layer="237" from-port="0" to-layer="238" to-port="1" />
+		<edge from-layer="238" from-port="2" to-layer="239" to-port="0" />
+		<edge from-layer="239" from-port="1" 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="243" to-port="1" />
+		<edge from-layer="243" from-port="2" to-layer="245" to-port="0" />
+		<edge from-layer="243" from-port="2" to-layer="277" to-port="0" />
+		<edge from-layer="244" from-port="0" to-layer="245" to-port="1" />
+		<edge from-layer="245" from-port="2" to-layer="247" to-port="0" />
+		<edge from-layer="246" from-port="0" to-layer="247" to-port="1" />
+		<edge from-layer="247" from-port="2" to-layer="249" to-port="0" />
+		<edge from-layer="248" from-port="0" to-layer="249" to-port="1" />
+		<edge from-layer="249" from-port="2" to-layer="260" to-port="0" />
+		<edge from-layer="250" from-port="0" to-layer="251" to-port="0" />
+		<edge from-layer="251" from-port="1" 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="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="1" to-layer="260" to-port="1" />
+		<edge from-layer="260" from-port="2" to-layer="262" to-port="0" />
+		<edge from-layer="261" from-port="0" to-layer="262" to-port="1" />
+		<edge from-layer="262" from-port="2" to-layer="263" to-port="0" />
+		<edge from-layer="263" from-port="1" to-layer="274" to-port="0" />
+		<edge from-layer="264" from-port="0" to-layer="265" to-port="0" />
+		<edge from-layer="265" from-port="1" to-layer="268" to-port="0" />
+		<edge from-layer="266" from-port="0" to-layer="267" to-port="0" />
+		<edge from-layer="267" from-port="1" 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="273" to-port="0" />
+		<edge from-layer="273" from-port="1" 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="277" to-port="1" />
+		<edge from-layer="277" from-port="2" to-layer="279" to-port="0" />
+		<edge from-layer="277" from-port="2" to-layer="354" to-port="0" />
+		<edge from-layer="278" from-port="0" to-layer="279" to-port="1" />
+		<edge from-layer="279" from-port="2" to-layer="281" to-port="0" />
+		<edge from-layer="280" from-port="0" to-layer="281" to-port="1" />
+		<edge from-layer="281" from-port="2" 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="294" to-port="0" />
+		<edge from-layer="283" from-port="2" to-layer="329" to-port="0" />
+		<edge from-layer="283" from-port="2" to-layer="311" to-port="0" />
+		<edge from-layer="284" from-port="0" to-layer="285" to-port="0" />
+		<edge from-layer="285" from-port="1" to-layer="288" to-port="0" />
+		<edge from-layer="286" from-port="0" to-layer="287" to-port="0" />
+		<edge from-layer="287" from-port="1" to-layer="288" to-port="1" />
+		<edge from-layer="288" from-port="2" to-layer="290" to-port="0" />
+		<edge from-layer="289" from-port="0" to-layer="290" to-port="1" />
+		<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="293" to-port="0" />
+		<edge from-layer="293" from-port="1" 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="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="316" to-port="0" />
+		<edge from-layer="301" from-port="0" to-layer="302" to-port="0" />
+		<edge from-layer="302" from-port="1" to-layer="305" to-port="0" />
+		<edge from-layer="303" from-port="0" to-layer="304" to-port="0" />
+		<edge from-layer="304" from-port="1" to-layer="305" to-port="1" />
+		<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="309" to-port="0" />
+		<edge from-layer="308" from-port="0" to-layer="309" to-port="1" />
+		<edge from-layer="309" from-port="2" to-layer="310" to-port="0" />
+		<edge from-layer="310" from-port="1" to-layer="311" to-port="1" />
+		<edge from-layer="311" from-port="2" to-layer="313" to-port="0" />
+		<edge from-layer="312" from-port="0" to-layer="313" to-port="1" />
+		<edge from-layer="313" from-port="2" to-layer="315" to-port="0" />
+		<edge from-layer="314" from-port="0" to-layer="315" to-port="1" />
+		<edge from-layer="315" from-port="2" to-layer="316" to-port="1" />
+		<edge from-layer="316" from-port="2" to-layer="317" to-port="0" />
+		<edge from-layer="317" from-port="2" to-layer="318" to-port="0" />
+		<edge from-layer="318" from-port="1" to-layer="336" to-port="0" />
+		<edge from-layer="319" from-port="0" 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="325" to-port="0" />
+		<edge from-layer="324" from-port="0" to-layer="325" to-port="1" />
+		<edge from-layer="325" from-port="2" to-layer="327" to-port="0" />
+		<edge from-layer="326" from-port="0" to-layer="327" to-port="1" />
+		<edge from-layer="327" from-port="2" to-layer="328" to-port="0" />
+		<edge from-layer="328" from-port="1" to-layer="329" to-port="1" />
+		<edge from-layer="329" from-port="2" to-layer="331" to-port="0" />
+		<edge from-layer="330" from-port="0" to-layer="331" to-port="1" />
+		<edge from-layer="331" from-port="2" to-layer="333" to-port="0" />
+		<edge from-layer="332" from-port="0" to-layer="333" to-port="1" />
+		<edge from-layer="333" from-port="2" to-layer="335" to-port="0" />
+		<edge from-layer="334" from-port="0" to-layer="335" to-port="1" />
+		<edge from-layer="335" from-port="2" to-layer="336" to-port="1" />
+		<edge from-layer="336" from-port="2" to-layer="338" to-port="0" />
+		<edge from-layer="337" from-port="0" to-layer="338" to-port="1" />
+		<edge from-layer="338" from-port="2" to-layer="340" to-port="0" />
+		<edge from-layer="339" from-port="0" to-layer="340" to-port="1" />
+		<edge from-layer="340" from-port="2" to-layer="351" to-port="0" />
+		<edge from-layer="341" from-port="0" to-layer="342" to-port="0" />
+		<edge from-layer="342" from-port="1" to-layer="345" to-port="0" />
+		<edge from-layer="343" from-port="0" to-layer="344" to-port="0" />
+		<edge from-layer="344" from-port="1" to-layer="345" to-port="1" />
+		<edge from-layer="345" from-port="2" to-layer="347" to-port="0" />
+		<edge from-layer="346" from-port="0" to-layer="347" to-port="1" />
+		<edge from-layer="347" from-port="2" to-layer="349" to-port="0" />
+		<edge from-layer="348" from-port="0" to-layer="349" to-port="1" />
+		<edge from-layer="349" from-port="2" to-layer="350" to-port="0" />
+		<edge from-layer="350" from-port="1" to-layer="351" to-port="1" />
+		<edge from-layer="351" from-port="2" to-layer="353" to-port="0" />
+		<edge from-layer="352" from-port="0" to-layer="353" to-port="1" />
+		<edge from-layer="353" from-port="2" to-layer="354" to-port="1" />
+		<edge from-layer="354" from-port="2" to-layer="428" to-port="0" />
+		<edge from-layer="354" from-port="2" to-layer="356" to-port="0" />
+		<edge from-layer="355" from-port="0" to-layer="356" to-port="1" />
+		<edge from-layer="356" from-port="2" to-layer="358" to-port="0" />
+		<edge from-layer="357" from-port="0" to-layer="358" to-port="1" />
+		<edge from-layer="358" from-port="2" to-layer="360" to-port="0" />
+		<edge from-layer="359" from-port="0" to-layer="360" to-port="1" />
+		<edge from-layer="360" from-port="2" to-layer="371" to-port="0" />
+		<edge from-layer="361" from-port="0" to-layer="362" to-port="0" />
+		<edge from-layer="362" from-port="1" to-layer="365" to-port="0" />
+		<edge from-layer="363" from-port="0" to-layer="364" to-port="0" />
+		<edge from-layer="364" from-port="1" to-layer="365" to-port="1" />
+		<edge from-layer="365" from-port="2" to-layer="367" to-port="0" />
+		<edge from-layer="366" from-port="0" to-layer="367" to-port="1" />
+		<edge from-layer="367" from-port="2" to-layer="369" to-port="0" />
+		<edge from-layer="368" from-port="0" to-layer="369" to-port="1" />
+		<edge from-layer="369" from-port="2" to-layer="370" to-port="0" />
+		<edge from-layer="370" from-port="1" to-layer="371" to-port="1" />
+		<edge from-layer="371" from-port="2" to-layer="373" to-port="0" />
+		<edge from-layer="372" from-port="0" to-layer="373" to-port="1" />
+		<edge from-layer="373" from-port="2" to-layer="375" to-port="0" />
+		<edge from-layer="374" from-port="0" to-layer="375" to-port="1" />
+		<edge from-layer="375" from-port="2" to-layer="377" to-port="0" />
+		<edge from-layer="376" from-port="0" to-layer="377" to-port="1" />
+		<edge from-layer="377" from-port="2" to-layer="392" to-port="0" />
+		<edge from-layer="378" from-port="0" to-layer="379" to-port="0" />
+		<edge from-layer="379" from-port="1" to-layer="382" to-port="0" />
+		<edge from-layer="380" from-port="0" to-layer="381" to-port="0" />
+		<edge from-layer="381" from-port="1" to-layer="382" to-port="1" />
+		<edge from-layer="382" from-port="2" to-layer="384" to-port="0" />
+		<edge from-layer="383" from-port="0" to-layer="384" to-port="1" />
+		<edge from-layer="384" from-port="2" to-layer="386" to-port="0" />
+		<edge from-layer="385" from-port="0" to-layer="386" to-port="1" />
+		<edge from-layer="386" from-port="2" to-layer="387" to-port="0" />
+		<edge from-layer="387" from-port="1" to-layer="388" to-port="1" />
+		<edge from-layer="388" from-port="2" to-layer="389" to-port="0" />
+		<edge from-layer="389" from-port="2" to-layer="391" to-port="0" />
+		<edge from-layer="390" from-port="0" to-layer="391" to-port="1" />
+		<edge from-layer="391" from-port="2" to-layer="392" to-port="1" />
+		<edge from-layer="392" from-port="2" to-layer="393" to-port="0" />
+		<edge from-layer="393" from-port="1" to-layer="410" to-port="0" />
+		<edge from-layer="394" from-port="0" to-layer="395" to-port="0" />
+		<edge from-layer="395" from-port="1" to-layer="398" to-port="0" />
+		<edge from-layer="396" from-port="0" to-layer="397" to-port="0" />
+		<edge from-layer="397" from-port="1" to-layer="398" to-port="1" />
+		<edge from-layer="398" from-port="2" to-layer="400" to-port="0" />
+		<edge from-layer="399" from-port="0" to-layer="400" to-port="1" />
+		<edge from-layer="400" from-port="2" to-layer="402" to-port="0" />
+		<edge from-layer="401" from-port="0" to-layer="402" to-port="1" />
+		<edge from-layer="402" from-port="2" to-layer="403" to-port="0" />
+		<edge from-layer="403" from-port="1" to-layer="404" to-port="1" />
+		<edge from-layer="404" from-port="2" to-layer="406" to-port="0" />
+		<edge from-layer="405" from-port="0" to-layer="406" to-port="1" />
+		<edge from-layer="406" from-port="2" to-layer="407" to-port="0" />
+		<edge from-layer="407" from-port="2" to-layer="409" to-port="0" />
+		<edge from-layer="408" from-port="0" to-layer="409" to-port="1" />
+		<edge from-layer="409" from-port="2" to-layer="410" to-port="1" />
+		<edge from-layer="410" from-port="2" to-layer="412" to-port="0" />
+		<edge from-layer="411" from-port="0" to-layer="412" to-port="1" />
+		<edge from-layer="412" from-port="2" to-layer="414" to-port="0" />
+		<edge from-layer="413" from-port="0" to-layer="414" to-port="1" />
+		<edge from-layer="414" from-port="2" to-layer="425" to-port="0" />
+		<edge from-layer="415" from-port="0" to-layer="416" to-port="0" />
+		<edge from-layer="416" from-port="1" to-layer="419" to-port="0" />
+		<edge from-layer="417" from-port="0" to-layer="418" to-port="0" />
+		<edge from-layer="418" from-port="1" to-layer="419" to-port="1" />
+		<edge from-layer="419" from-port="2" to-layer="421" to-port="0" />
+		<edge from-layer="420" from-port="0" to-layer="421" to-port="1" />
+		<edge from-layer="421" from-port="2" to-layer="423" to-port="0" />
+		<edge from-layer="422" from-port="0" to-layer="423" to-port="1" />
+		<edge from-layer="423" from-port="2" to-layer="424" to-port="0" />
+		<edge from-layer="424" from-port="1" to-layer="425" to-port="1" />
+		<edge from-layer="425" from-port="2" to-layer="427" to-port="0" />
+		<edge from-layer="426" from-port="0" to-layer="427" to-port="1" />
+		<edge from-layer="427" from-port="2" to-layer="428" to-port="1" />
+		<edge from-layer="428" from-port="2" to-layer="430" to-port="0" />
+		<edge from-layer="428" from-port="2" to-layer="462" to-port="0" />
+		<edge from-layer="429" from-port="0" to-layer="430" to-port="1" />
+		<edge from-layer="430" from-port="2" to-layer="432" to-port="0" />
+		<edge from-layer="431" from-port="0" to-layer="432" to-port="1" />
+		<edge from-layer="432" from-port="2" to-layer="434" to-port="0" />
+		<edge from-layer="433" from-port="0" to-layer="434" to-port="1" />
+		<edge from-layer="434" from-port="2" to-layer="445" to-port="0" />
+		<edge from-layer="435" from-port="0" to-layer="436" to-port="0" />
+		<edge from-layer="436" from-port="1" to-layer="439" to-port="0" />
+		<edge from-layer="437" from-port="0" to-layer="438" to-port="0" />
+		<edge from-layer="438" from-port="1" to-layer="439" to-port="1" />
+		<edge from-layer="439" from-port="2" to-layer="441" to-port="0" />
+		<edge from-layer="440" from-port="0" to-layer="441" to-port="1" />
+		<edge from-layer="441" from-port="2" to-layer="443" to-port="0" />
+		<edge from-layer="442" from-port="0" to-layer="443" to-port="1" />
+		<edge from-layer="443" from-port="2" to-layer="444" to-port="0" />
+		<edge from-layer="444" from-port="1" to-layer="445" to-port="1" />
+		<edge from-layer="445" from-port="2" to-layer="447" to-port="0" />
+		<edge from-layer="446" from-port="0" to-layer="447" to-port="1" />
+		<edge from-layer="447" from-port="2" to-layer="448" to-port="0" />
+		<edge from-layer="448" from-port="1" to-layer="459" to-port="0" />
+		<edge from-layer="449" from-port="0" to-layer="450" to-port="0" />
+		<edge from-layer="450" from-port="1" to-layer="453" to-port="0" />
+		<edge from-layer="451" from-port="0" to-layer="452" to-port="0" />
+		<edge from-layer="452" from-port="1" to-layer="453" to-port="1" />
+		<edge from-layer="453" from-port="2" to-layer="455" to-port="0" />
+		<edge from-layer="454" from-port="0" to-layer="455" to-port="1" />
+		<edge from-layer="455" from-port="2" to-layer="457" to-port="0" />
+		<edge from-layer="456" from-port="0" to-layer="457" to-port="1" />
+		<edge from-layer="457" from-port="2" to-layer="458" to-port="0" />
+		<edge from-layer="458" from-port="1" to-layer="459" to-port="1" />
+		<edge from-layer="459" from-port="2" to-layer="461" to-port="0" />
+		<edge from-layer="460" from-port="0" to-layer="461" to-port="1" />
+		<edge from-layer="461" from-port="2" to-layer="462" to-port="1" />
+		<edge from-layer="462" from-port="2" to-layer="539" to-port="0" />
+		<edge from-layer="462" from-port="2" to-layer="464" to-port="0" />
+		<edge from-layer="463" from-port="0" to-layer="464" to-port="1" />
+		<edge from-layer="464" from-port="2" to-layer="466" to-port="0" />
+		<edge from-layer="465" from-port="0" to-layer="466" to-port="1" />
+		<edge from-layer="466" from-port="2" to-layer="468" to-port="0" />
+		<edge from-layer="467" from-port="0" to-layer="468" to-port="1" />
+		<edge from-layer="468" from-port="2" to-layer="496" to-port="0" />
+		<edge from-layer="468" from-port="2" to-layer="479" to-port="0" />
+		<edge from-layer="468" from-port="2" to-layer="514" to-port="0" />
+		<edge from-layer="469" from-port="0" to-layer="470" to-port="0" />
+		<edge from-layer="470" from-port="1" to-layer="473" to-port="0" />
+		<edge from-layer="471" from-port="0" to-layer="472" to-port="0" />
+		<edge from-layer="472" from-port="1" to-layer="473" to-port="1" />
+		<edge from-layer="473" from-port="2" to-layer="475" to-port="0" />
+		<edge from-layer="474" from-port="0" to-layer="475" to-port="1" />
+		<edge from-layer="475" from-port="2" to-layer="477" to-port="0" />
+		<edge from-layer="476" from-port="0" to-layer="477" to-port="1" />
+		<edge from-layer="477" from-port="2" to-layer="478" to-port="0" />
+		<edge from-layer="478" from-port="1" to-layer="479" to-port="1" />
+		<edge from-layer="479" from-port="2" to-layer="481" to-port="0" />
+		<edge from-layer="480" from-port="0" to-layer="481" to-port="1" />
+		<edge from-layer="481" from-port="2" to-layer="483" to-port="0" />
+		<edge from-layer="482" from-port="0" to-layer="483" to-port="1" />
+		<edge from-layer="483" from-port="2" to-layer="485" to-port="0" />
+		<edge from-layer="484" from-port="0" to-layer="485" to-port="1" />
+		<edge from-layer="485" from-port="2" to-layer="501" to-port="0" />
+		<edge from-layer="486" from-port="0" to-layer="487" to-port="0" />
+		<edge from-layer="487" from-port="1" to-layer="490" to-port="0" />
+		<edge from-layer="488" from-port="0" to-layer="489" to-port="0" />
+		<edge from-layer="489" from-port="1" to-layer="490" to-port="1" />
+		<edge from-layer="490" from-port="2" to-layer="492" to-port="0" />
+		<edge from-layer="491" from-port="0" to-layer="492" to-port="1" />
+		<edge from-layer="492" from-port="2" to-layer="494" to-port="0" />
+		<edge from-layer="493" from-port="0" to-layer="494" to-port="1" />
+		<edge from-layer="494" from-port="2" to-layer="495" to-port="0" />
+		<edge from-layer="495" from-port="1" to-layer="496" to-port="1" />
+		<edge from-layer="496" from-port="2" to-layer="498" to-port="0" />
+		<edge from-layer="497" from-port="0" to-layer="498" to-port="1" />
+		<edge from-layer="498" from-port="2" to-layer="500" to-port="0" />
+		<edge from-layer="499" from-port="0" to-layer="500" to-port="1" />
+		<edge from-layer="500" from-port="2" to-layer="501" to-port="1" />
+		<edge from-layer="501" from-port="2" to-layer="502" to-port="0" />
+		<edge from-layer="502" from-port="2" to-layer="503" to-port="0" />
+		<edge from-layer="503" from-port="1" to-layer="521" to-port="0" />
+		<edge from-layer="504" from-port="0" to-layer="505" to-port="0" />
+		<edge from-layer="505" from-port="1" to-layer="508" to-port="0" />
+		<edge from-layer="506" from-port="0" to-layer="507" to-port="0" />
+		<edge from-layer="507" from-port="1" to-layer="508" to-port="1" />
+		<edge from-layer="508" from-port="2" to-layer="510" to-port="0" />
+		<edge from-layer="509" from-port="0" to-layer="510" to-port="1" />
+		<edge from-layer="510" from-port="2" to-layer="512" to-port="0" />
+		<edge from-layer="511" from-port="0" to-layer="512" to-port="1" />
+		<edge from-layer="512" from-port="2" to-layer="513" to-port="0" />
+		<edge from-layer="513" from-port="1" to-layer="514" to-port="1" />
+		<edge from-layer="514" from-port="2" to-layer="516" to-port="0" />
+		<edge from-layer="515" from-port="0" to-layer="516" to-port="1" />
+		<edge from-layer="516" from-port="2" to-layer="518" to-port="0" />
+		<edge from-layer="517" from-port="0" to-layer="518" to-port="1" />
+		<edge from-layer="518" from-port="2" to-layer="520" to-port="0" />
+		<edge from-layer="519" from-port="0" to-layer="520" to-port="1" />
+		<edge from-layer="520" from-port="2" to-layer="521" to-port="1" />
+		<edge from-layer="521" from-port="2" to-layer="523" to-port="0" />
+		<edge from-layer="522" from-port="0" to-layer="523" to-port="1" />
+		<edge from-layer="523" from-port="2" to-layer="525" to-port="0" />
+		<edge from-layer="524" from-port="0" to-layer="525" to-port="1" />
+		<edge from-layer="525" from-port="2" to-layer="536" to-port="0" />
+		<edge from-layer="526" from-port="0" to-layer="527" to-port="0" />
+		<edge from-layer="527" from-port="1" to-layer="530" to-port="0" />
+		<edge from-layer="528" from-port="0" to-layer="529" to-port="0" />
+		<edge from-layer="529" from-port="1" to-layer="530" to-port="1" />
+		<edge from-layer="530" from-port="2" to-layer="532" to-port="0" />
+		<edge from-layer="531" from-port="0" to-layer="532" to-port="1" />
+		<edge from-layer="532" from-port="2" to-layer="534" to-port="0" />
+		<edge from-layer="533" from-port="0" to-layer="534" to-port="1" />
+		<edge from-layer="534" from-port="2" to-layer="535" to-port="0" />
+		<edge from-layer="535" from-port="1" to-layer="536" to-port="1" />
+		<edge from-layer="536" from-port="2" to-layer="538" to-port="0" />
+		<edge from-layer="537" from-port="0" to-layer="538" to-port="1" />
+		<edge from-layer="538" from-port="2" to-layer="539" to-port="1" />
+		<edge from-layer="539" from-port="2" to-layer="541" to-port="0" />
+		<edge from-layer="539" from-port="2" to-layer="613" to-port="0" />
+		<edge from-layer="540" from-port="0" to-layer="541" to-port="1" />
+		<edge from-layer="541" from-port="2" to-layer="543" to-port="0" />
+		<edge from-layer="542" from-port="0" to-layer="543" to-port="1" />
+		<edge from-layer="543" from-port="2" to-layer="545" to-port="0" />
+		<edge from-layer="544" from-port="0" to-layer="545" to-port="1" />
+		<edge from-layer="545" from-port="2" to-layer="556" to-port="0" />
+		<edge from-layer="546" from-port="0" to-layer="547" to-port="0" />
+		<edge from-layer="547" from-port="1" to-layer="550" to-port="0" />
+		<edge from-layer="548" from-port="0" to-layer="549" to-port="0" />
+		<edge from-layer="549" from-port="1" to-layer="550" to-port="1" />
+		<edge from-layer="550" from-port="2" to-layer="552" to-port="0" />
+		<edge from-layer="551" from-port="0" to-layer="552" to-port="1" />
+		<edge from-layer="552" from-port="2" to-layer="554" to-port="0" />
+		<edge from-layer="553" from-port="0" to-layer="554" to-port="1" />
+		<edge from-layer="554" from-port="2" to-layer="555" to-port="0" />
+		<edge from-layer="555" from-port="1" to-layer="556" to-port="1" />
+		<edge from-layer="556" from-port="2" to-layer="558" to-port="0" />
+		<edge from-layer="557" from-port="0" to-layer="558" to-port="1" />
+		<edge from-layer="558" from-port="2" to-layer="560" to-port="0" />
+		<edge from-layer="559" from-port="0" to-layer="560" to-port="1" />
+		<edge from-layer="560" from-port="2" to-layer="562" to-port="0" />
+		<edge from-layer="561" from-port="0" to-layer="562" to-port="1" />
+		<edge from-layer="562" from-port="2" to-layer="577" to-port="0" />
+		<edge from-layer="563" from-port="0" to-layer="564" to-port="0" />
+		<edge from-layer="564" from-port="1" to-layer="567" to-port="0" />
+		<edge from-layer="565" from-port="0" to-layer="566" to-port="0" />
+		<edge from-layer="566" from-port="1" to-layer="567" to-port="1" />
+		<edge from-layer="567" from-port="2" to-layer="569" to-port="0" />
+		<edge from-layer="568" from-port="0" to-layer="569" to-port="1" />
+		<edge from-layer="569" from-port="2" to-layer="571" to-port="0" />
+		<edge from-layer="570" from-port="0" to-layer="571" to-port="1" />
+		<edge from-layer="571" from-port="2" to-layer="572" to-port="0" />
+		<edge from-layer="572" from-port="1" to-layer="573" to-port="1" />
+		<edge from-layer="573" from-port="2" to-layer="574" to-port="0" />
+		<edge from-layer="574" from-port="2" to-layer="576" to-port="0" />
+		<edge from-layer="575" from-port="0" to-layer="576" to-port="1" />
+		<edge from-layer="576" from-port="2" to-layer="577" to-port="1" />
+		<edge from-layer="577" from-port="2" to-layer="578" to-port="0" />
+		<edge from-layer="578" from-port="1" to-layer="595" to-port="0" />
+		<edge from-layer="579" from-port="0" to-layer="580" to-port="0" />
+		<edge from-layer="580" from-port="1" to-layer="583" to-port="0" />
+		<edge from-layer="581" from-port="0" to-layer="582" to-port="0" />
+		<edge from-layer="582" from-port="1" to-layer="583" to-port="1" />
+		<edge from-layer="583" from-port="2" to-layer="585" to-port="0" />
+		<edge from-layer="584" from-port="0" to-layer="585" to-port="1" />
+		<edge from-layer="585" from-port="2" to-layer="587" to-port="0" />
+		<edge from-layer="586" from-port="0" to-layer="587" to-port="1" />
+		<edge from-layer="587" from-port="2" to-layer="588" to-port="0" />
+		<edge from-layer="588" from-port="1" to-layer="589" to-port="1" />
+		<edge from-layer="589" from-port="2" to-layer="591" to-port="0" />
+		<edge from-layer="590" from-port="0" to-layer="591" to-port="1" />
+		<edge from-layer="591" from-port="2" to-layer="592" to-port="0" />
+		<edge from-layer="592" from-port="2" to-layer="594" to-port="0" />
+		<edge from-layer="593" from-port="0" to-layer="594" to-port="1" />
+		<edge from-layer="594" from-port="2" to-layer="595" to-port="1" />
+		<edge from-layer="595" from-port="2" to-layer="597" to-port="0" />
+		<edge from-layer="596" from-port="0" to-layer="597" to-port="1" />
+		<edge from-layer="597" from-port="2" to-layer="599" to-port="0" />
+		<edge from-layer="598" from-port="0" to-layer="599" to-port="1" />
+		<edge from-layer="599" from-port="2" to-layer="610" to-port="0" />
+		<edge from-layer="600" from-port="0" to-layer="601" to-port="0" />
+		<edge from-layer="601" from-port="1" to-layer="604" to-port="0" />
+		<edge from-layer="602" from-port="0" to-layer="603" to-port="0" />
+		<edge from-layer="603" from-port="1" to-layer="604" to-port="1" />
+		<edge from-layer="604" from-port="2" to-layer="606" to-port="0" />
+		<edge from-layer="605" from-port="0" to-layer="606" to-port="1" />
+		<edge from-layer="606" from-port="2" to-layer="608" to-port="0" />
+		<edge from-layer="607" from-port="0" to-layer="608" to-port="1" />
+		<edge from-layer="608" from-port="2" to-layer="609" to-port="0" />
+		<edge from-layer="609" from-port="1" to-layer="610" to-port="1" />
+		<edge from-layer="610" from-port="2" to-layer="612" to-port="0" />
+		<edge from-layer="611" from-port="0" to-layer="612" to-port="1" />
+		<edge from-layer="612" from-port="2" to-layer="613" to-port="1" />
+		<edge from-layer="613" from-port="2" to-layer="647" to-port="0" />
+		<edge from-layer="613" from-port="2" to-layer="615" to-port="0" />
+		<edge from-layer="614" from-port="0" to-layer="615" to-port="1" />
+		<edge from-layer="615" from-port="2" to-layer="617" to-port="0" />
+		<edge from-layer="616" from-port="0" to-layer="617" to-port="1" />
+		<edge from-layer="617" from-port="2" to-layer="619" to-port="0" />
+		<edge from-layer="618" from-port="0" to-layer="619" to-port="1" />
+		<edge from-layer="619" from-port="2" to-layer="630" to-port="0" />
+		<edge from-layer="620" from-port="0" to-layer="621" to-port="0" />
+		<edge from-layer="621" from-port="1" to-layer="624" to-port="0" />
+		<edge from-layer="622" from-port="0" to-layer="623" to-port="0" />
+		<edge from-layer="623" from-port="1" to-layer="624" to-port="1" />
+		<edge from-layer="624" from-port="2" to-layer="626" to-port="0" />
+		<edge from-layer="625" from-port="0" to-layer="626" to-port="1" />
+		<edge from-layer="626" from-port="2" to-layer="628" to-port="0" />
+		<edge from-layer="627" from-port="0" to-layer="628" to-port="1" />
+		<edge from-layer="628" from-port="2" to-layer="629" to-port="0" />
+		<edge from-layer="629" from-port="1" to-layer="630" to-port="1" />
+		<edge from-layer="630" from-port="2" to-layer="632" to-port="0" />
+		<edge from-layer="631" from-port="0" to-layer="632" to-port="1" />
+		<edge from-layer="632" from-port="2" to-layer="633" to-port="0" />
+		<edge from-layer="633" from-port="1" to-layer="644" to-port="0" />
+		<edge from-layer="634" from-port="0" to-layer="635" to-port="0" />
+		<edge from-layer="635" from-port="1" to-layer="638" to-port="0" />
+		<edge from-layer="636" from-port="0" to-layer="637" to-port="0" />
+		<edge from-layer="637" from-port="1" to-layer="638" to-port="1" />
+		<edge from-layer="638" from-port="2" to-layer="640" to-port="0" />
+		<edge from-layer="639" from-port="0" to-layer="640" to-port="1" />
+		<edge from-layer="640" from-port="2" to-layer="642" to-port="0" />
+		<edge from-layer="641" from-port="0" to-layer="642" to-port="1" />
+		<edge from-layer="642" from-port="2" to-layer="643" to-port="0" />
+		<edge from-layer="643" from-port="1" to-layer="644" to-port="1" />
+		<edge from-layer="644" from-port="2" to-layer="646" to-port="0" />
+		<edge from-layer="645" from-port="0" to-layer="646" to-port="1" />
+		<edge from-layer="646" from-port="2" to-layer="647" to-port="1" />
+		<edge from-layer="647" from-port="2" to-layer="724" to-port="0" />
+		<edge from-layer="647" from-port="2" to-layer="649" to-port="0" />
+		<edge from-layer="648" from-port="0" to-layer="649" to-port="1" />
+		<edge from-layer="649" from-port="2" to-layer="651" to-port="0" />
+		<edge from-layer="650" from-port="0" to-layer="651" to-port="1" />
+		<edge from-layer="651" from-port="2" to-layer="653" to-port="0" />
+		<edge from-layer="652" from-port="0" to-layer="653" to-port="1" />
+		<edge from-layer="653" from-port="2" to-layer="681" to-port="0" />
+		<edge from-layer="653" from-port="2" to-layer="699" to-port="0" />
+		<edge from-layer="653" from-port="2" to-layer="664" to-port="0" />
+		<edge from-layer="654" from-port="0" to-layer="655" to-port="0" />
+		<edge from-layer="655" from-port="1" to-layer="658" to-port="0" />
+		<edge from-layer="656" from-port="0" to-layer="657" to-port="0" />
+		<edge from-layer="657" from-port="1" to-layer="658" to-port="1" />
+		<edge from-layer="658" from-port="2" to-layer="660" to-port="0" />
+		<edge from-layer="659" from-port="0" to-layer="660" to-port="1" />
+		<edge from-layer="660" from-port="2" to-layer="662" to-port="0" />
+		<edge from-layer="661" from-port="0" to-layer="662" to-port="1" />
+		<edge from-layer="662" from-port="2" to-layer="663" to-port="0" />
+		<edge from-layer="663" from-port="1" to-layer="664" to-port="1" />
+		<edge from-layer="664" from-port="2" to-layer="666" to-port="0" />
+		<edge from-layer="665" from-port="0" to-layer="666" to-port="1" />
+		<edge from-layer="666" from-port="2" to-layer="668" to-port="0" />
+		<edge from-layer="667" from-port="0" to-layer="668" to-port="1" />
+		<edge from-layer="668" from-port="2" to-layer="670" to-port="0" />
+		<edge from-layer="669" from-port="0" to-layer="670" to-port="1" />
+		<edge from-layer="670" from-port="2" to-layer="686" to-port="0" />
+		<edge from-layer="671" from-port="0" to-layer="672" to-port="0" />
+		<edge from-layer="672" from-port="1" to-layer="675" to-port="0" />
+		<edge from-layer="673" from-port="0" to-layer="674" to-port="0" />
+		<edge from-layer="674" from-port="1" to-layer="675" to-port="1" />
+		<edge from-layer="675" from-port="2" to-layer="677" to-port="0" />
+		<edge from-layer="676" from-port="0" to-layer="677" to-port="1" />
+		<edge from-layer="677" from-port="2" to-layer="679" to-port="0" />
+		<edge from-layer="678" from-port="0" to-layer="679" to-port="1" />
+		<edge from-layer="679" from-port="2" to-layer="680" to-port="0" />
+		<edge from-layer="680" from-port="1" to-layer="681" to-port="1" />
+		<edge from-layer="681" from-port="2" to-layer="683" to-port="0" />
+		<edge from-layer="682" from-port="0" to-layer="683" to-port="1" />
+		<edge from-layer="683" from-port="2" to-layer="685" to-port="0" />
+		<edge from-layer="684" from-port="0" to-layer="685" to-port="1" />
+		<edge from-layer="685" from-port="2" to-layer="686" to-port="1" />
+		<edge from-layer="686" from-port="2" to-layer="687" to-port="0" />
+		<edge from-layer="687" from-port="2" to-layer="688" to-port="0" />
+		<edge from-layer="688" from-port="1" to-layer="706" to-port="0" />
+		<edge from-layer="689" from-port="0" to-layer="690" to-port="0" />
+		<edge from-layer="690" from-port="1" to-layer="693" to-port="0" />
+		<edge from-layer="691" from-port="0" to-layer="692" to-port="0" />
+		<edge from-layer="692" from-port="1" to-layer="693" to-port="1" />
+		<edge from-layer="693" from-port="2" to-layer="695" to-port="0" />
+		<edge from-layer="694" from-port="0" to-layer="695" to-port="1" />
+		<edge from-layer="695" from-port="2" to-layer="697" to-port="0" />
+		<edge from-layer="696" from-port="0" to-layer="697" to-port="1" />
+		<edge from-layer="697" from-port="2" to-layer="698" to-port="0" />
+		<edge from-layer="698" from-port="1" to-layer="699" to-port="1" />
+		<edge from-layer="699" from-port="2" to-layer="701" to-port="0" />
+		<edge from-layer="700" from-port="0" to-layer="701" to-port="1" />
+		<edge from-layer="701" from-port="2" to-layer="703" to-port="0" />
+		<edge from-layer="702" from-port="0" to-layer="703" to-port="1" />
+		<edge from-layer="703" from-port="2" to-layer="705" to-port="0" />
+		<edge from-layer="704" from-port="0" to-layer="705" to-port="1" />
+		<edge from-layer="705" from-port="2" to-layer="706" to-port="1" />
+		<edge from-layer="706" from-port="2" to-layer="708" to-port="0" />
+		<edge from-layer="707" from-port="0" to-layer="708" to-port="1" />
+		<edge from-layer="708" from-port="2" to-layer="710" to-port="0" />
+		<edge from-layer="709" from-port="0" to-layer="710" to-port="1" />
+		<edge from-layer="710" from-port="2" to-layer="721" to-port="0" />
+		<edge from-layer="711" from-port="0" to-layer="712" to-port="0" />
+		<edge from-layer="712" from-port="1" to-layer="715" to-port="0" />
+		<edge from-layer="713" from-port="0" to-layer="714" to-port="0" />
+		<edge from-layer="714" from-port="1" to-layer="715" to-port="1" />
+		<edge from-layer="715" from-port="2" to-layer="717" to-port="0" />
+		<edge from-layer="716" from-port="0" to-layer="717" to-port="1" />
+		<edge from-layer="717" from-port="2" to-layer="719" to-port="0" />
+		<edge from-layer="718" from-port="0" to-layer="719" to-port="1" />
+		<edge from-layer="719" from-port="2" to-layer="720" to-port="0" />
+		<edge from-layer="720" from-port="1" to-layer="721" to-port="1" />
+		<edge from-layer="721" from-port="2" to-layer="723" to-port="0" />
+		<edge from-layer="722" from-port="0" to-layer="723" to-port="1" />
+		<edge from-layer="723" from-port="2" to-layer="724" to-port="1" />
+		<edge from-layer="724" from-port="2" to-layer="798" to-port="0" />
+		<edge from-layer="724" from-port="2" to-layer="726" to-port="0" />
+		<edge from-layer="725" from-port="0" to-layer="726" to-port="1" />
+		<edge from-layer="726" from-port="2" to-layer="728" to-port="0" />
+		<edge from-layer="727" from-port="0" to-layer="728" to-port="1" />
+		<edge from-layer="728" from-port="2" to-layer="730" to-port="0" />
+		<edge from-layer="729" from-port="0" to-layer="730" to-port="1" />
+		<edge from-layer="730" from-port="2" to-layer="741" to-port="0" />
+		<edge from-layer="731" from-port="0" to-layer="732" to-port="0" />
+		<edge from-layer="732" from-port="1" to-layer="735" to-port="0" />
+		<edge from-layer="733" from-port="0" to-layer="734" to-port="0" />
+		<edge from-layer="734" from-port="1" to-layer="735" to-port="1" />
+		<edge from-layer="735" from-port="2" to-layer="737" to-port="0" />
+		<edge from-layer="736" from-port="0" to-layer="737" to-port="1" />
+		<edge from-layer="737" from-port="2" to-layer="739" to-port="0" />
+		<edge from-layer="738" from-port="0" to-layer="739" to-port="1" />
+		<edge from-layer="739" from-port="2" to-layer="740" to-port="0" />
+		<edge from-layer="740" from-port="1" to-layer="741" to-port="1" />
+		<edge from-layer="741" from-port="2" to-layer="743" to-port="0" />
+		<edge from-layer="742" from-port="0" to-layer="743" to-port="1" />
+		<edge from-layer="743" from-port="2" to-layer="745" to-port="0" />
+		<edge from-layer="744" from-port="0" to-layer="745" to-port="1" />
+		<edge from-layer="745" from-port="2" to-layer="747" to-port="0" />
+		<edge from-layer="746" from-port="0" to-layer="747" to-port="1" />
+		<edge from-layer="747" from-port="2" to-layer="762" to-port="0" />
+		<edge from-layer="748" from-port="0" to-layer="749" to-port="0" />
+		<edge from-layer="749" from-port="1" to-layer="752" to-port="0" />
+		<edge from-layer="750" from-port="0" to-layer="751" to-port="0" />
+		<edge from-layer="751" from-port="1" to-layer="752" to-port="1" />
+		<edge from-layer="752" from-port="2" to-layer="754" to-port="0" />
+		<edge from-layer="753" from-port="0" to-layer="754" to-port="1" />
+		<edge from-layer="754" from-port="2" to-layer="756" to-port="0" />
+		<edge from-layer="755" from-port="0" to-layer="756" to-port="1" />
+		<edge from-layer="756" from-port="2" to-layer="757" to-port="0" />
+		<edge from-layer="757" from-port="1" to-layer="758" to-port="1" />
+		<edge from-layer="758" from-port="2" to-layer="759" to-port="0" />
+		<edge from-layer="759" from-port="2" to-layer="761" to-port="0" />
+		<edge from-layer="760" from-port="0" to-layer="761" to-port="1" />
+		<edge from-layer="761" from-port="2" to-layer="762" to-port="1" />
+		<edge from-layer="762" from-port="2" to-layer="763" to-port="0" />
+		<edge from-layer="763" from-port="1" to-layer="780" to-port="0" />
+		<edge from-layer="764" from-port="0" to-layer="765" to-port="0" />
+		<edge from-layer="765" from-port="1" to-layer="768" to-port="0" />
+		<edge from-layer="766" from-port="0" to-layer="767" to-port="0" />
+		<edge from-layer="767" from-port="1" to-layer="768" to-port="1" />
+		<edge from-layer="768" from-port="2" to-layer="770" to-port="0" />
+		<edge from-layer="769" from-port="0" to-layer="770" to-port="1" />
+		<edge from-layer="770" from-port="2" to-layer="772" to-port="0" />
+		<edge from-layer="771" from-port="0" to-layer="772" to-port="1" />
+		<edge from-layer="772" from-port="2" to-layer="773" to-port="0" />
+		<edge from-layer="773" from-port="1" to-layer="774" to-port="1" />
+		<edge from-layer="774" from-port="2" to-layer="776" to-port="0" />
+		<edge from-layer="775" from-port="0" to-layer="776" to-port="1" />
+		<edge from-layer="776" from-port="2" to-layer="777" to-port="0" />
+		<edge from-layer="777" from-port="2" to-layer="779" to-port="0" />
+		<edge from-layer="778" from-port="0" to-layer="779" to-port="1" />
+		<edge from-layer="779" from-port="2" to-layer="780" to-port="1" />
+		<edge from-layer="780" from-port="2" to-layer="782" to-port="0" />
+		<edge from-layer="781" from-port="0" to-layer="782" to-port="1" />
+		<edge from-layer="782" from-port="2" to-layer="784" to-port="0" />
+		<edge from-layer="783" from-port="0" to-layer="784" to-port="1" />
+		<edge from-layer="784" from-port="2" to-layer="795" to-port="0" />
+		<edge from-layer="785" from-port="0" to-layer="786" to-port="0" />
+		<edge from-layer="786" from-port="1" to-layer="789" to-port="0" />
+		<edge from-layer="787" from-port="0" to-layer="788" to-port="0" />
+		<edge from-layer="788" from-port="1" to-layer="789" to-port="1" />
+		<edge from-layer="789" from-port="2" to-layer="791" to-port="0" />
+		<edge from-layer="790" from-port="0" to-layer="791" to-port="1" />
+		<edge from-layer="791" from-port="2" to-layer="793" to-port="0" />
+		<edge from-layer="792" from-port="0" to-layer="793" to-port="1" />
+		<edge from-layer="793" from-port="2" to-layer="794" to-port="0" />
+		<edge from-layer="794" from-port="1" to-layer="795" to-port="1" />
+		<edge from-layer="795" from-port="2" to-layer="797" to-port="0" />
+		<edge from-layer="796" from-port="0" to-layer="797" to-port="1" />
+		<edge from-layer="797" from-port="2" to-layer="798" to-port="1" />
+		<edge from-layer="798" from-port="2" to-layer="800" to-port="0" />
+		<edge from-layer="798" from-port="2" to-layer="832" to-port="0" />
+		<edge from-layer="799" from-port="0" to-layer="800" to-port="1" />
+		<edge from-layer="800" from-port="2" to-layer="802" to-port="0" />
+		<edge from-layer="801" from-port="0" to-layer="802" to-port="1" />
+		<edge from-layer="802" from-port="2" to-layer="804" to-port="0" />
+		<edge from-layer="803" from-port="0" to-layer="804" to-port="1" />
+		<edge from-layer="804" from-port="2" to-layer="815" to-port="0" />
+		<edge from-layer="805" from-port="0" to-layer="806" to-port="0" />
+		<edge from-layer="806" from-port="1" to-layer="809" to-port="0" />
+		<edge from-layer="807" from-port="0" to-layer="808" to-port="0" />
+		<edge from-layer="808" from-port="1" to-layer="809" to-port="1" />
+		<edge from-layer="809" from-port="2" to-layer="811" to-port="0" />
+		<edge from-layer="810" from-port="0" to-layer="811" to-port="1" />
+		<edge from-layer="811" from-port="2" to-layer="813" to-port="0" />
+		<edge from-layer="812" from-port="0" to-layer="813" to-port="1" />
+		<edge from-layer="813" from-port="2" to-layer="814" to-port="0" />
+		<edge from-layer="814" from-port="1" to-layer="815" to-port="1" />
+		<edge from-layer="815" from-port="2" to-layer="817" to-port="0" />
+		<edge from-layer="816" from-port="0" to-layer="817" to-port="1" />
+		<edge from-layer="817" from-port="2" to-layer="818" to-port="0" />
+		<edge from-layer="818" from-port="1" to-layer="829" to-port="0" />
+		<edge from-layer="819" from-port="0" to-layer="820" to-port="0" />
+		<edge from-layer="820" from-port="1" to-layer="823" to-port="0" />
+		<edge from-layer="821" from-port="0" to-layer="822" to-port="0" />
+		<edge from-layer="822" from-port="1" to-layer="823" to-port="1" />
+		<edge from-layer="823" from-port="2" to-layer="825" to-port="0" />
+		<edge from-layer="824" from-port="0" to-layer="825" to-port="1" />
+		<edge from-layer="825" from-port="2" to-layer="827" to-port="0" />
+		<edge from-layer="826" from-port="0" to-layer="827" to-port="1" />
+		<edge from-layer="827" from-port="2" to-layer="828" to-port="0" />
+		<edge from-layer="828" from-port="1" to-layer="829" to-port="1" />
+		<edge from-layer="829" from-port="2" to-layer="831" to-port="0" />
+		<edge from-layer="830" from-port="0" to-layer="831" to-port="1" />
+		<edge from-layer="831" from-port="2" to-layer="832" to-port="1" />
+		<edge from-layer="832" from-port="2" to-layer="909" to-port="0" />
+		<edge from-layer="832" from-port="2" to-layer="834" to-port="0" />
+		<edge from-layer="833" from-port="0" to-layer="834" to-port="1" />
+		<edge from-layer="834" from-port="2" to-layer="836" to-port="0" />
+		<edge from-layer="835" from-port="0" to-layer="836" to-port="1" />
+		<edge from-layer="836" from-port="2" to-layer="838" to-port="0" />
+		<edge from-layer="837" from-port="0" to-layer="838" to-port="1" />
+		<edge from-layer="838" from-port="2" to-layer="884" to-port="0" />
+		<edge from-layer="838" from-port="2" to-layer="866" to-port="0" />
+		<edge from-layer="838" from-port="2" to-layer="849" to-port="0" />
+		<edge from-layer="839" from-port="0" to-layer="840" to-port="0" />
+		<edge from-layer="840" from-port="1" to-layer="843" to-port="0" />
+		<edge from-layer="841" from-port="0" to-layer="842" to-port="0" />
+		<edge from-layer="842" from-port="1" to-layer="843" to-port="1" />
+		<edge from-layer="843" from-port="2" to-layer="845" to-port="0" />
+		<edge from-layer="844" from-port="0" to-layer="845" to-port="1" />
+		<edge from-layer="845" from-port="2" to-layer="847" to-port="0" />
+		<edge from-layer="846" from-port="0" to-layer="847" to-port="1" />
+		<edge from-layer="847" from-port="2" to-layer="848" to-port="0" />
+		<edge from-layer="848" from-port="1" to-layer="849" to-port="1" />
+		<edge from-layer="849" from-port="2" to-layer="851" to-port="0" />
+		<edge from-layer="850" from-port="0" to-layer="851" to-port="1" />
+		<edge from-layer="851" from-port="2" to-layer="853" to-port="0" />
+		<edge from-layer="852" from-port="0" to-layer="853" to-port="1" />
+		<edge from-layer="853" from-port="2" to-layer="855" to-port="0" />
+		<edge from-layer="854" from-port="0" to-layer="855" to-port="1" />
+		<edge from-layer="855" from-port="2" to-layer="871" to-port="0" />
+		<edge from-layer="856" from-port="0" to-layer="857" to-port="0" />
+		<edge from-layer="857" from-port="1" to-layer="860" to-port="0" />
+		<edge from-layer="858" from-port="0" to-layer="859" to-port="0" />
+		<edge from-layer="859" from-port="1" to-layer="860" to-port="1" />
+		<edge from-layer="860" from-port="2" to-layer="862" to-port="0" />
+		<edge from-layer="861" from-port="0" to-layer="862" to-port="1" />
+		<edge from-layer="862" from-port="2" to-layer="864" to-port="0" />
+		<edge from-layer="863" from-port="0" to-layer="864" to-port="1" />
+		<edge from-layer="864" from-port="2" to-layer="865" to-port="0" />
+		<edge from-layer="865" from-port="1" to-layer="866" to-port="1" />
+		<edge from-layer="866" from-port="2" to-layer="868" to-port="0" />
+		<edge from-layer="867" from-port="0" to-layer="868" to-port="1" />
+		<edge from-layer="868" from-port="2" to-layer="870" to-port="0" />
+		<edge from-layer="869" from-port="0" to-layer="870" to-port="1" />
+		<edge from-layer="870" from-port="2" to-layer="871" to-port="1" />
+		<edge from-layer="871" from-port="2" to-layer="872" to-port="0" />
+		<edge from-layer="872" from-port="2" to-layer="873" to-port="0" />
+		<edge from-layer="873" from-port="1" to-layer="891" to-port="0" />
+		<edge from-layer="874" from-port="0" to-layer="875" to-port="0" />
+		<edge from-layer="875" from-port="1" to-layer="878" to-port="0" />
+		<edge from-layer="876" from-port="0" to-layer="877" to-port="0" />
+		<edge from-layer="877" from-port="1" to-layer="878" to-port="1" />
+		<edge from-layer="878" from-port="2" to-layer="880" to-port="0" />
+		<edge from-layer="879" from-port="0" to-layer="880" to-port="1" />
+		<edge from-layer="880" from-port="2" to-layer="882" to-port="0" />
+		<edge from-layer="881" from-port="0" to-layer="882" to-port="1" />
+		<edge from-layer="882" from-port="2" to-layer="883" to-port="0" />
+		<edge from-layer="883" from-port="1" to-layer="884" to-port="1" />
+		<edge from-layer="884" from-port="2" to-layer="886" to-port="0" />
+		<edge from-layer="885" from-port="0" to-layer="886" to-port="1" />
+		<edge from-layer="886" from-port="2" to-layer="888" to-port="0" />
+		<edge from-layer="887" from-port="0" to-layer="888" to-port="1" />
+		<edge from-layer="888" from-port="2" to-layer="890" to-port="0" />
+		<edge from-layer="889" from-port="0" to-layer="890" to-port="1" />
+		<edge from-layer="890" from-port="2" to-layer="891" to-port="1" />
+		<edge from-layer="891" from-port="2" to-layer="893" to-port="0" />
+		<edge from-layer="892" from-port="0" to-layer="893" to-port="1" />
+		<edge from-layer="893" from-port="2" to-layer="895" to-port="0" />
+		<edge from-layer="894" from-port="0" to-layer="895" to-port="1" />
+		<edge from-layer="895" from-port="2" to-layer="906" to-port="0" />
+		<edge from-layer="896" from-port="0" to-layer="897" to-port="0" />
+		<edge from-layer="897" from-port="1" to-layer="900" to-port="0" />
+		<edge from-layer="898" from-port="0" to-layer="899" to-port="0" />
+		<edge from-layer="899" from-port="1" to-layer="900" to-port="1" />
+		<edge from-layer="900" from-port="2" to-layer="902" to-port="0" />
+		<edge from-layer="901" from-port="0" to-layer="902" to-port="1" />
+		<edge from-layer="902" from-port="2" to-layer="904" to-port="0" />
+		<edge from-layer="903" from-port="0" to-layer="904" to-port="1" />
+		<edge from-layer="904" from-port="2" to-layer="905" to-port="0" />
+		<edge from-layer="905" from-port="1" to-layer="906" to-port="1" />
+		<edge from-layer="906" from-port="2" to-layer="908" to-port="0" />
+		<edge from-layer="907" from-port="0" to-layer="908" to-port="1" />
+		<edge from-layer="908" from-port="2" to-layer="909" to-port="1" />
+		<edge from-layer="909" from-port="2" to-layer="911" to-port="0" />
+		<edge from-layer="909" from-port="2" to-layer="983" to-port="0" />
+		<edge from-layer="910" from-port="0" to-layer="911" to-port="1" />
+		<edge from-layer="911" from-port="2" to-layer="913" to-port="0" />
+		<edge from-layer="912" from-port="0" to-layer="913" to-port="1" />
+		<edge from-layer="913" from-port="2" to-layer="915" to-port="0" />
+		<edge from-layer="914" from-port="0" to-layer="915" to-port="1" />
+		<edge from-layer="915" from-port="2" to-layer="926" to-port="0" />
+		<edge from-layer="916" from-port="0" to-layer="917" to-port="0" />
+		<edge from-layer="917" from-port="1" to-layer="920" to-port="0" />
+		<edge from-layer="918" from-port="0" to-layer="919" to-port="0" />
+		<edge from-layer="919" from-port="1" to-layer="920" to-port="1" />
+		<edge from-layer="920" from-port="2" to-layer="922" to-port="0" />
+		<edge from-layer="921" from-port="0" to-layer="922" to-port="1" />
+		<edge from-layer="922" from-port="2" to-layer="924" to-port="0" />
+		<edge from-layer="923" from-port="0" to-layer="924" to-port="1" />
+		<edge from-layer="924" from-port="2" to-layer="925" to-port="0" />
+		<edge from-layer="925" from-port="1" to-layer="926" to-port="1" />
+		<edge from-layer="926" from-port="2" to-layer="928" to-port="0" />
+		<edge from-layer="927" from-port="0" to-layer="928" to-port="1" />
+		<edge from-layer="928" from-port="2" to-layer="930" to-port="0" />
+		<edge from-layer="929" from-port="0" to-layer="930" to-port="1" />
+		<edge from-layer="930" from-port="2" to-layer="932" to-port="0" />
+		<edge from-layer="931" from-port="0" to-layer="932" to-port="1" />
+		<edge from-layer="932" from-port="2" to-layer="947" to-port="0" />
+		<edge from-layer="933" from-port="0" to-layer="934" to-port="0" />
+		<edge from-layer="934" from-port="1" to-layer="937" to-port="0" />
+		<edge from-layer="935" from-port="0" to-layer="936" to-port="0" />
+		<edge from-layer="936" from-port="1" to-layer="937" to-port="1" />
+		<edge from-layer="937" from-port="2" to-layer="939" to-port="0" />
+		<edge from-layer="938" from-port="0" to-layer="939" to-port="1" />
+		<edge from-layer="939" from-port="2" to-layer="941" to-port="0" />
+		<edge from-layer="940" from-port="0" to-layer="941" to-port="1" />
+		<edge from-layer="941" from-port="2" to-layer="942" to-port="0" />
+		<edge from-layer="942" from-port="1" to-layer="943" to-port="1" />
+		<edge from-layer="943" from-port="2" to-layer="944" to-port="0" />
+		<edge from-layer="944" from-port="2" to-layer="946" to-port="0" />
+		<edge from-layer="945" from-port="0" to-layer="946" to-port="1" />
+		<edge from-layer="946" from-port="2" to-layer="947" to-port="1" />
+		<edge from-layer="947" from-port="2" to-layer="948" to-port="0" />
+		<edge from-layer="948" from-port="1" to-layer="965" to-port="0" />
+		<edge from-layer="949" from-port="0" to-layer="950" to-port="0" />
+		<edge from-layer="950" from-port="1" to-layer="953" to-port="0" />
+		<edge from-layer="951" from-port="0" to-layer="952" to-port="0" />
+		<edge from-layer="952" from-port="1" to-layer="953" to-port="1" />
+		<edge from-layer="953" from-port="2" to-layer="955" to-port="0" />
+		<edge from-layer="954" from-port="0" to-layer="955" to-port="1" />
+		<edge from-layer="955" from-port="2" to-layer="957" to-port="0" />
+		<edge from-layer="956" from-port="0" to-layer="957" to-port="1" />
+		<edge from-layer="957" from-port="2" to-layer="958" to-port="0" />
+		<edge from-layer="958" from-port="1" to-layer="959" to-port="1" />
+		<edge from-layer="959" from-port="2" to-layer="961" to-port="0" />
+		<edge from-layer="960" from-port="0" to-layer="961" to-port="1" />
+		<edge from-layer="961" from-port="2" to-layer="962" to-port="0" />
+		<edge from-layer="962" from-port="2" to-layer="964" to-port="0" />
+		<edge from-layer="963" from-port="0" to-layer="964" to-port="1" />
+		<edge from-layer="964" from-port="2" to-layer="965" to-port="1" />
+		<edge from-layer="965" from-port="2" to-layer="967" to-port="0" />
+		<edge from-layer="966" from-port="0" to-layer="967" to-port="1" />
+		<edge from-layer="967" from-port="2" to-layer="969" to-port="0" />
+		<edge from-layer="968" from-port="0" to-layer="969" to-port="1" />
+		<edge from-layer="969" from-port="2" to-layer="980" to-port="0" />
+		<edge from-layer="970" from-port="0" to-layer="971" to-port="0" />
+		<edge from-layer="971" from-port="1" to-layer="974" to-port="0" />
+		<edge from-layer="972" from-port="0" to-layer="973" to-port="0" />
+		<edge from-layer="973" from-port="1" to-layer="974" to-port="1" />
+		<edge from-layer="974" from-port="2" to-layer="976" to-port="0" />
+		<edge from-layer="975" from-port="0" to-layer="976" to-port="1" />
+		<edge from-layer="976" from-port="2" to-layer="978" to-port="0" />
+		<edge from-layer="977" from-port="0" to-layer="978" to-port="1" />
+		<edge from-layer="978" from-port="2" to-layer="979" to-port="0" />
+		<edge from-layer="979" from-port="1" to-layer="980" to-port="1" />
+		<edge from-layer="980" from-port="2" to-layer="982" to-port="0" />
+		<edge from-layer="981" from-port="0" to-layer="982" to-port="1" />
+		<edge from-layer="982" from-port="2" to-layer="983" to-port="1" />
+		<edge from-layer="983" from-port="2" to-layer="1017" to-port="0" />
+		<edge from-layer="983" from-port="2" to-layer="985" to-port="0" />
+		<edge from-layer="984" from-port="0" to-layer="985" to-port="1" />
+		<edge from-layer="985" from-port="2" to-layer="987" to-port="0" />
+		<edge from-layer="986" from-port="0" to-layer="987" to-port="1" />
+		<edge from-layer="987" from-port="2" to-layer="989" to-port="0" />
+		<edge from-layer="988" from-port="0" to-layer="989" to-port="1" />
+		<edge from-layer="989" from-port="2" to-layer="1000" to-port="0" />
+		<edge from-layer="990" from-port="0" to-layer="991" to-port="0" />
+		<edge from-layer="991" from-port="1" to-layer="994" to-port="0" />
+		<edge from-layer="992" from-port="0" to-layer="993" to-port="0" />
+		<edge from-layer="993" from-port="1" to-layer="994" to-port="1" />
+		<edge from-layer="994" from-port="2" to-layer="996" to-port="0" />
+		<edge from-layer="995" from-port="0" to-layer="996" to-port="1" />
+		<edge from-layer="996" from-port="2" to-layer="998" to-port="0" />
+		<edge from-layer="997" from-port="0" to-layer="998" to-port="1" />
+		<edge from-layer="998" from-port="2" to-layer="999" to-port="0" />
+		<edge from-layer="999" from-port="1" to-layer="1000" to-port="1" />
+		<edge from-layer="1000" from-port="2" to-layer="1002" to-port="0" />
+		<edge from-layer="1001" from-port="0" to-layer="1002" to-port="1" />
+		<edge from-layer="1002" from-port="2" to-layer="1003" to-port="0" />
+		<edge from-layer="1003" from-port="1" to-layer="1014" to-port="0" />
+		<edge from-layer="1004" from-port="0" to-layer="1005" to-port="0" />
+		<edge from-layer="1005" from-port="1" to-layer="1008" to-port="0" />
+		<edge from-layer="1006" from-port="0" to-layer="1007" to-port="0" />
+		<edge from-layer="1007" from-port="1" to-layer="1008" to-port="1" />
+		<edge from-layer="1008" from-port="2" to-layer="1010" to-port="0" />
+		<edge from-layer="1009" from-port="0" to-layer="1010" to-port="1" />
+		<edge from-layer="1010" from-port="2" to-layer="1012" to-port="0" />
+		<edge from-layer="1011" from-port="0" to-layer="1012" to-port="1" />
+		<edge from-layer="1012" from-port="2" to-layer="1013" to-port="0" />
+		<edge from-layer="1013" from-port="1" to-layer="1014" to-port="1" />
+		<edge from-layer="1014" from-port="2" to-layer="1016" to-port="0" />
+		<edge from-layer="1015" from-port="0" to-layer="1016" to-port="1" />
+		<edge from-layer="1016" from-port="2" to-layer="1017" to-port="1" />
+		<edge from-layer="1017" from-port="2" to-layer="1094" to-port="0" />
+		<edge from-layer="1017" from-port="2" to-layer="1019" to-port="0" />
+		<edge from-layer="1018" from-port="0" to-layer="1019" to-port="1" />
+		<edge from-layer="1019" from-port="2" to-layer="1021" to-port="0" />
+		<edge from-layer="1020" from-port="0" to-layer="1021" to-port="1" />
+		<edge from-layer="1021" from-port="2" to-layer="1023" to-port="0" />
+		<edge from-layer="1022" from-port="0" to-layer="1023" to-port="1" />
+		<edge from-layer="1023" from-port="2" to-layer="1069" to-port="0" />
+		<edge from-layer="1023" from-port="2" to-layer="1034" to-port="0" />
+		<edge from-layer="1023" from-port="2" to-layer="1051" to-port="0" />
+		<edge from-layer="1024" from-port="0" to-layer="1025" to-port="0" />
+		<edge from-layer="1025" from-port="1" to-layer="1028" to-port="0" />
+		<edge from-layer="1026" from-port="0" to-layer="1027" to-port="0" />
+		<edge from-layer="1027" from-port="1" to-layer="1028" to-port="1" />
+		<edge from-layer="1028" from-port="2" to-layer="1030" to-port="0" />
+		<edge from-layer="1029" from-port="0" to-layer="1030" to-port="1" />
+		<edge from-layer="1030" from-port="2" to-layer="1032" to-port="0" />
+		<edge from-layer="1031" from-port="0" to-layer="1032" to-port="1" />
+		<edge from-layer="1032" from-port="2" to-layer="1033" to-port="0" />
+		<edge from-layer="1033" from-port="1" to-layer="1034" to-port="1" />
+		<edge from-layer="1034" from-port="2" to-layer="1036" to-port="0" />
+		<edge from-layer="1035" from-port="0" to-layer="1036" to-port="1" />
+		<edge from-layer="1036" from-port="2" to-layer="1038" to-port="0" />
+		<edge from-layer="1037" from-port="0" to-layer="1038" to-port="1" />
+		<edge from-layer="1038" from-port="2" to-layer="1040" to-port="0" />
+		<edge from-layer="1039" from-port="0" to-layer="1040" to-port="1" />
+		<edge from-layer="1040" from-port="2" to-layer="1056" to-port="0" />
+		<edge from-layer="1041" from-port="0" to-layer="1042" to-port="0" />
+		<edge from-layer="1042" from-port="1" to-layer="1045" to-port="0" />
+		<edge from-layer="1043" from-port="0" to-layer="1044" to-port="0" />
+		<edge from-layer="1044" from-port="1" to-layer="1045" to-port="1" />
+		<edge from-layer="1045" from-port="2" to-layer="1047" to-port="0" />
+		<edge from-layer="1046" from-port="0" to-layer="1047" to-port="1" />
+		<edge from-layer="1047" from-port="2" to-layer="1049" to-port="0" />
+		<edge from-layer="1048" from-port="0" to-layer="1049" to-port="1" />
+		<edge from-layer="1049" from-port="2" to-layer="1050" to-port="0" />
+		<edge from-layer="1050" from-port="1" to-layer="1051" to-port="1" />
+		<edge from-layer="1051" from-port="2" to-layer="1053" to-port="0" />
+		<edge from-layer="1052" from-port="0" to-layer="1053" to-port="1" />
+		<edge from-layer="1053" from-port="2" to-layer="1055" to-port="0" />
+		<edge from-layer="1054" from-port="0" to-layer="1055" to-port="1" />
+		<edge from-layer="1055" from-port="2" to-layer="1056" to-port="1" />
+		<edge from-layer="1056" from-port="2" to-layer="1057" to-port="0" />
+		<edge from-layer="1057" from-port="2" to-layer="1058" to-port="0" />
+		<edge from-layer="1058" from-port="1" to-layer="1076" to-port="0" />
+		<edge from-layer="1059" from-port="0" to-layer="1060" to-port="0" />
+		<edge from-layer="1060" from-port="1" to-layer="1063" to-port="0" />
+		<edge from-layer="1061" from-port="0" to-layer="1062" to-port="0" />
+		<edge from-layer="1062" from-port="1" to-layer="1063" to-port="1" />
+		<edge from-layer="1063" from-port="2" to-layer="1065" to-port="0" />
+		<edge from-layer="1064" from-port="0" to-layer="1065" to-port="1" />
+		<edge from-layer="1065" from-port="2" to-layer="1067" to-port="0" />
+		<edge from-layer="1066" from-port="0" to-layer="1067" to-port="1" />
+		<edge from-layer="1067" from-port="2" to-layer="1068" to-port="0" />
+		<edge from-layer="1068" from-port="1" to-layer="1069" to-port="1" />
+		<edge from-layer="1069" from-port="2" to-layer="1071" to-port="0" />
+		<edge from-layer="1070" from-port="0" to-layer="1071" to-port="1" />
+		<edge from-layer="1071" from-port="2" to-layer="1073" to-port="0" />
+		<edge from-layer="1072" from-port="0" to-layer="1073" to-port="1" />
+		<edge from-layer="1073" from-port="2" to-layer="1075" to-port="0" />
+		<edge from-layer="1074" from-port="0" to-layer="1075" to-port="1" />
+		<edge from-layer="1075" from-port="2" to-layer="1076" to-port="1" />
+		<edge from-layer="1076" from-port="2" to-layer="1078" to-port="0" />
+		<edge from-layer="1077" from-port="0" to-layer="1078" to-port="1" />
+		<edge from-layer="1078" from-port="2" to-layer="1080" to-port="0" />
+		<edge from-layer="1079" from-port="0" to-layer="1080" to-port="1" />
+		<edge from-layer="1080" from-port="2" to-layer="1091" to-port="0" />
+		<edge from-layer="1081" from-port="0" to-layer="1082" to-port="0" />
+		<edge from-layer="1082" from-port="1" to-layer="1085" to-port="0" />
+		<edge from-layer="1083" from-port="0" to-layer="1084" to-port="0" />
+		<edge from-layer="1084" from-port="1" to-layer="1085" to-port="1" />
+		<edge from-layer="1085" from-port="2" to-layer="1087" to-port="0" />
+		<edge from-layer="1086" from-port="0" to-layer="1087" to-port="1" />
+		<edge from-layer="1087" from-port="2" to-layer="1089" to-port="0" />
+		<edge from-layer="1088" from-port="0" to-layer="1089" to-port="1" />
+		<edge from-layer="1089" from-port="2" to-layer="1090" to-port="0" />
+		<edge from-layer="1090" from-port="1" to-layer="1091" to-port="1" />
+		<edge from-layer="1091" from-port="2" to-layer="1093" to-port="0" />
+		<edge from-layer="1092" from-port="0" to-layer="1093" to-port="1" />
+		<edge from-layer="1093" from-port="2" to-layer="1094" to-port="1" />
+		<edge from-layer="1094" from-port="2" to-layer="1096" to-port="0" />
+		<edge from-layer="1094" from-port="2" to-layer="1168" to-port="0" />
+		<edge from-layer="1095" from-port="0" to-layer="1096" to-port="1" />
+		<edge from-layer="1096" from-port="2" to-layer="1098" to-port="0" />
+		<edge from-layer="1097" from-port="0" to-layer="1098" to-port="1" />
+		<edge from-layer="1098" from-port="2" to-layer="1100" to-port="0" />
+		<edge from-layer="1099" from-port="0" to-layer="1100" to-port="1" />
+		<edge from-layer="1100" from-port="2" to-layer="1111" to-port="0" />
+		<edge from-layer="1101" from-port="0" to-layer="1102" to-port="0" />
+		<edge from-layer="1102" from-port="1" to-layer="1105" to-port="0" />
+		<edge from-layer="1103" from-port="0" to-layer="1104" to-port="0" />
+		<edge from-layer="1104" from-port="1" to-layer="1105" to-port="1" />
+		<edge from-layer="1105" from-port="2" to-layer="1107" to-port="0" />
+		<edge from-layer="1106" from-port="0" to-layer="1107" to-port="1" />
+		<edge from-layer="1107" from-port="2" to-layer="1109" to-port="0" />
+		<edge from-layer="1108" from-port="0" to-layer="1109" to-port="1" />
+		<edge from-layer="1109" from-port="2" to-layer="1110" to-port="0" />
+		<edge from-layer="1110" from-port="1" to-layer="1111" to-port="1" />
+		<edge from-layer="1111" from-port="2" to-layer="1113" to-port="0" />
+		<edge from-layer="1112" from-port="0" to-layer="1113" to-port="1" />
+		<edge from-layer="1113" from-port="2" to-layer="1115" to-port="0" />
+		<edge from-layer="1114" from-port="0" to-layer="1115" to-port="1" />
+		<edge from-layer="1115" from-port="2" to-layer="1117" to-port="0" />
+		<edge from-layer="1116" from-port="0" to-layer="1117" to-port="1" />
+		<edge from-layer="1117" from-port="2" to-layer="1132" to-port="0" />
+		<edge from-layer="1118" from-port="0" to-layer="1119" to-port="0" />
+		<edge from-layer="1119" from-port="1" to-layer="1122" to-port="0" />
+		<edge from-layer="1120" from-port="0" to-layer="1121" to-port="0" />
+		<edge from-layer="1121" from-port="1" to-layer="1122" to-port="1" />
+		<edge from-layer="1122" from-port="2" to-layer="1124" to-port="0" />
+		<edge from-layer="1123" from-port="0" to-layer="1124" to-port="1" />
+		<edge from-layer="1124" from-port="2" to-layer="1126" to-port="0" />
+		<edge from-layer="1125" from-port="0" to-layer="1126" to-port="1" />
+		<edge from-layer="1126" from-port="2" to-layer="1127" to-port="0" />
+		<edge from-layer="1127" from-port="1" to-layer="1128" to-port="1" />
+		<edge from-layer="1128" from-port="2" to-layer="1129" to-port="0" />
+		<edge from-layer="1129" from-port="2" to-layer="1131" to-port="0" />
+		<edge from-layer="1130" from-port="0" to-layer="1131" to-port="1" />
+		<edge from-layer="1131" from-port="2" to-layer="1132" to-port="1" />
+		<edge from-layer="1132" from-port="2" to-layer="1133" to-port="0" />
+		<edge from-layer="1133" from-port="1" to-layer="1150" to-port="0" />
+		<edge from-layer="1134" from-port="0" to-layer="1135" to-port="0" />
+		<edge from-layer="1135" from-port="1" to-layer="1138" to-port="0" />
+		<edge from-layer="1136" from-port="0" to-layer="1137" to-port="0" />
+		<edge from-layer="1137" from-port="1" to-layer="1138" to-port="1" />
+		<edge from-layer="1138" from-port="2" to-layer="1140" to-port="0" />
+		<edge from-layer="1139" from-port="0" to-layer="1140" to-port="1" />
+		<edge from-layer="1140" from-port="2" to-layer="1142" to-port="0" />
+		<edge from-layer="1141" from-port="0" to-layer="1142" to-port="1" />
+		<edge from-layer="1142" from-port="2" to-layer="1143" to-port="0" />
+		<edge from-layer="1143" from-port="1" to-layer="1144" to-port="1" />
+		<edge from-layer="1144" from-port="2" to-layer="1146" to-port="0" />
+		<edge from-layer="1145" from-port="0" to-layer="1146" to-port="1" />
+		<edge from-layer="1146" from-port="2" to-layer="1147" to-port="0" />
+		<edge from-layer="1147" from-port="2" to-layer="1149" to-port="0" />
+		<edge from-layer="1148" from-port="0" to-layer="1149" to-port="1" />
+		<edge from-layer="1149" from-port="2" to-layer="1150" to-port="1" />
+		<edge from-layer="1150" from-port="2" to-layer="1152" to-port="0" />
+		<edge from-layer="1151" from-port="0" to-layer="1152" to-port="1" />
+		<edge from-layer="1152" from-port="2" to-layer="1154" to-port="0" />
+		<edge from-layer="1153" from-port="0" to-layer="1154" to-port="1" />
+		<edge from-layer="1154" from-port="2" to-layer="1165" to-port="0" />
+		<edge from-layer="1155" from-port="0" to-layer="1156" to-port="0" />
+		<edge from-layer="1156" from-port="1" to-layer="1159" to-port="0" />
+		<edge from-layer="1157" from-port="0" to-layer="1158" to-port="0" />
+		<edge from-layer="1158" from-port="1" to-layer="1159" to-port="1" />
+		<edge from-layer="1159" from-port="2" to-layer="1161" to-port="0" />
+		<edge from-layer="1160" from-port="0" to-layer="1161" to-port="1" />
+		<edge from-layer="1161" from-port="2" to-layer="1163" to-port="0" />
+		<edge from-layer="1162" from-port="0" to-layer="1163" to-port="1" />
+		<edge from-layer="1163" from-port="2" to-layer="1164" to-port="0" />
+		<edge from-layer="1164" from-port="1" to-layer="1165" to-port="1" />
+		<edge from-layer="1165" from-port="2" to-layer="1167" to-port="0" />
+		<edge from-layer="1166" from-port="0" to-layer="1167" to-port="1" />
+		<edge from-layer="1167" from-port="2" to-layer="1168" to-port="1" />
+		<edge from-layer="1168" from-port="2" to-layer="1170" to-port="0" />
+		<edge from-layer="1168" from-port="2" to-layer="1202" to-port="0" />
+		<edge from-layer="1169" from-port="0" to-layer="1170" to-port="1" />
+		<edge from-layer="1170" from-port="2" to-layer="1172" to-port="0" />
+		<edge from-layer="1171" from-port="0" to-layer="1172" to-port="1" />
+		<edge from-layer="1172" from-port="2" to-layer="1174" to-port="0" />
+		<edge from-layer="1173" from-port="0" to-layer="1174" to-port="1" />
+		<edge from-layer="1174" from-port="2" to-layer="1185" to-port="0" />
+		<edge from-layer="1175" from-port="0" to-layer="1176" to-port="0" />
+		<edge from-layer="1176" from-port="1" to-layer="1179" to-port="0" />
+		<edge from-layer="1177" from-port="0" to-layer="1178" to-port="0" />
+		<edge from-layer="1178" from-port="1" to-layer="1179" to-port="1" />
+		<edge from-layer="1179" from-port="2" to-layer="1181" to-port="0" />
+		<edge from-layer="1180" from-port="0" to-layer="1181" to-port="1" />
+		<edge from-layer="1181" from-port="2" to-layer="1183" to-port="0" />
+		<edge from-layer="1182" from-port="0" to-layer="1183" to-port="1" />
+		<edge from-layer="1183" from-port="2" to-layer="1184" to-port="0" />
+		<edge from-layer="1184" from-port="1" to-layer="1185" to-port="1" />
+		<edge from-layer="1185" from-port="2" to-layer="1187" to-port="0" />
+		<edge from-layer="1186" from-port="0" to-layer="1187" to-port="1" />
+		<edge from-layer="1187" from-port="2" to-layer="1188" to-port="0" />
+		<edge from-layer="1188" from-port="1" to-layer="1199" to-port="0" />
+		<edge from-layer="1189" from-port="0" to-layer="1190" to-port="0" />
+		<edge from-layer="1190" from-port="1" to-layer="1193" to-port="0" />
+		<edge from-layer="1191" from-port="0" to-layer="1192" to-port="0" />
+		<edge from-layer="1192" from-port="1" to-layer="1193" to-port="1" />
+		<edge from-layer="1193" from-port="2" to-layer="1195" to-port="0" />
+		<edge from-layer="1194" from-port="0" to-layer="1195" to-port="1" />
+		<edge from-layer="1195" from-port="2" to-layer="1197" to-port="0" />
+		<edge from-layer="1196" from-port="0" to-layer="1197" to-port="1" />
+		<edge from-layer="1197" from-port="2" to-layer="1198" to-port="0" />
+		<edge from-layer="1198" from-port="1" to-layer="1199" to-port="1" />
+		<edge from-layer="1199" from-port="2" to-layer="1201" to-port="0" />
+		<edge from-layer="1200" from-port="0" to-layer="1201" to-port="1" />
+		<edge from-layer="1201" from-port="2" to-layer="1202" to-port="1" />
+		<edge from-layer="1202" from-port="2" to-layer="1204" to-port="0" />
+		<edge from-layer="1203" from-port="0" to-layer="1204" to-port="1" />
+		<edge from-layer="1204" from-port="2" to-layer="1206" to-port="0" />
+		<edge from-layer="1205" from-port="0" to-layer="1206" to-port="1" />
+		<edge from-layer="1206" from-port="2" to-layer="1208" to-port="0" />
+		<edge from-layer="1207" from-port="0" to-layer="1208" to-port="1" />
+		<edge from-layer="1208" from-port="2" to-layer="1209" to-port="0" />
+		<edge from-layer="1209" from-port="2" to-layer="1210" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2024.5.0-16901-32aaa2fbd96" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<weight_compression>
+				<advanced_parameters value="{'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<gptq value="False" />
+				<group_size value="128" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int4_asym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<optimum_intel_version value="1.20.0.dev0+2559620" />
+			<optimum_version value="1.23.1" />
+			<pytorch_version value="2.5.0" />
+			<transformers_version value="4.45.2" />
+		</optimum>
+	</rt_info>
+</net>