diff --git "a/openvino_model.xml" "b/openvino_model.xml"
new file mode 100644--- /dev/null
+++ "b/openvino_model.xml"
@@ -0,0 +1,12570 @@
+<?xml version="1.0"?>
+<net name="Model0" version="11">
+	<layers>
+		<layer id="2" name="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="1" name="attention_mask" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="attention_mask">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="0" name="token_type_ids" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="token_type_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.embeddings.word_embeddings.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="30522, 384" offset="0" size="11720448" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Convert_6277" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="self.embeddings.word_embeddings.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="30522, 1" offset="11720448" size="30522" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>30522</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Convert_6280" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>30522</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>30522</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="self.embeddings.word_embeddings.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>30522</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="self.embeddings.word_embeddings.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="30522, 1" offset="11750970" size="61044" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>30522</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="self.embeddings.word_embeddings.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>30522</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="self.embeddings.word_embeddings.weight/fq_weights_0/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>30522</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="__module.embeddings.word_embeddings/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="12" name="__module.embeddings.word_embeddings/aten::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="11812014" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="13" name="__module.embeddings.word_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>30522</dim>
+					<dim>384</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="79,inputs_embeds">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="self.embeddings.token_type_embeddings.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="2, 384" offset="11812018" size="768" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Convert_6695" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="self.embeddings.token_type_embeddings.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="2, 1" offset="11812786" size="2" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>2</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Convert_6698" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>2</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>2</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="self.embeddings.token_type_embeddings.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="self.embeddings.token_type_embeddings.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="2, 1" offset="11812788" size="4" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>2</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="self.embeddings.token_type_embeddings.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>2</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="self.embeddings.token_type_embeddings.weight/fq_weights_0/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="__module.embeddings.token_type_embeddings/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="23" name="__module.embeddings.token_type_embeddings/aten::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="11812014" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="24" name="__module.embeddings.token_type_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>2</dim>
+					<dim>384</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="81,token_type_embeddings.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="__module.embeddings/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="82_1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="self.embeddings.position_embeddings.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 384" offset="11812792" size="196608" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Convert_6420" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="self.embeddings.position_embeddings.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1" offset="12009400" size="512" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="Convert_6423" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="self.embeddings.position_embeddings.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="self.embeddings.position_embeddings.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1" offset="12009912" size="1024" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="self.embeddings.position_embeddings.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="self.embeddings.position_embeddings.weight/fq_weights_0/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="__module.embeddings/aten::slice/Slice" type="Const" version="opset1">
+			<data element_type="i64" shape="1, 512" offset="12010936" size="4096" />
+			<output>
+				<port id="0" precision="I64" names="76">
+					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="__module.embeddings/aten::slice/Reshape" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="ShapeOf_6086" 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="37" name="Constant_6207" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015040" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Constant_6088" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="39" name="Gather_6089" 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="10,72,74,75,8">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="40" name="__module.embeddings/aten::slice/Reshape_2" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015040" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="41" name="__module.embeddings/aten::slice/Reshape_3" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015040" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="42" name="__module.embeddings/aten::slice/Slice_1" type="Slice" version="opset8">
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>512</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="I64" names="77">
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="43" name="__module.embeddings.position_embeddings/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="44" name="__module.embeddings.position_embeddings/aten::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="11812014" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="45" name="__module.embeddings.position_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>512</dim>
+					<dim>384</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="84,position_embeddings.1">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="__module.embeddings/aten::add_/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="82,embeddings.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="__module.embeddings.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="48" name="__module.embeddings.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="49" name="Constant_5961" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12015052" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="50" name="__module.embeddings.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="51" name="Constant_5962" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12016588" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="52" name="__module.embeddings.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="89,input.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="53" name="self.encoder.layer.0.attention.self.query.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="12018124" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="54" name="Convert_6452" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="55" name="self.encoder.layer.0.attention.self.query.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="12091852" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="56" name="Convert_6454" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="57" name="self.encoder.layer.0.attention.self.query.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="58" name="self.encoder.layer.0.attention.self.query.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="12092428" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="59" name="self.encoder.layer.0.attention.self.query.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="60" name="Constant_6459" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="61" name="Reshape_6460" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="62" name="self.encoder.layer.0.attention.self.query.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="63" name="__module.encoder.layer.0.attention.self.query/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="64" name="Constant_5963" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12094740" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="65" name="__module.encoder.layer.0.attention.self.query/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="129,x.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="66" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="67" name="__module.encoder.layer.0.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="133,x.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="68" name="Constant_247" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="134">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="69" name="__module.encoder.layer.0.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="135">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="70" name="self.encoder.layer.0.attention.self.key.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="12096340" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="71" name="Convert_6441" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="72" name="self.encoder.layer.0.attention.self.key.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="12170068" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="73" name="Convert_6443" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="74" name="self.encoder.layer.0.attention.self.key.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="75" name="self.encoder.layer.0.attention.self.key.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="12170644" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="76" name="self.encoder.layer.0.attention.self.key.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="77" name="Constant_6448" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="78" name="Reshape_6449" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="79" name="self.encoder.layer.0.attention.self.key.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="80" name="__module.encoder.layer.0.attention.self.key/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="81" name="Constant_5964" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12172948" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="82" name="__module.encoder.layer.0.attention.self.key/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="138,x.5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="83" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="84" name="__module.encoder.layer.0.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="142,x.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="85" name="Constant_272" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="143">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="86" name="__module.encoder.layer.0.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="144">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="87" name="self.encoder.layer.0.attention.self.value.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="12174484" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="88" name="Convert_6430" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="89" name="self.encoder.layer.0.attention.self.value.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="12248212" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="90" name="Convert_6432" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="91" name="self.encoder.layer.0.attention.self.value.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="92" name="self.encoder.layer.0.attention.self.value.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="12248788" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="93" name="self.encoder.layer.0.attention.self.value.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="94" name="Constant_6437" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="95" name="Reshape_6438" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="96" name="self.encoder.layer.0.attention.self.value.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="97" name="__module.encoder.layer.0.attention.self.value/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="98" name="Constant_5965" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12251092" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="99" name="__module.encoder.layer.0.attention.self.value/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="147,x.9">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="100" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="101" name="__module.encoder.layer.0.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="151,x.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="102" name="Constant_297" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="152">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="103" name="__module.encoder.layer.0.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="153">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="104" name="Constant_5967" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1, 1" offset="12252628" size="4" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="105" name="25" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015040" size="8" />
+			<output>
+				<port id="0" precision="I64" names="25" />
+			</output>
+		</layer>
+		<layer id="106" name="aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" names="26">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="107" name="27" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12252632" size="8" />
+			<output>
+				<port id="0" precision="I64" names="27" />
+			</output>
+		</layer>
+		<layer id="108" name="aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" names="28,33">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="109" name="ShapeOf_6094" 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="110" name="Constant_6210" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="111" name="Constant_6096" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="112" name="Gather_6097" 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="13,15">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="113" name="Constant_5191" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015040" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="114" name="Constant_6213" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12015040" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="115" name="Constant_6104" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="116" name="Gather_6105" 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="17,19">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="117" name="prim::ListConstruct/Concat" 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" names="35">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="118" name="aten::expand/Broadcast" type="Broadcast" version="opset3">
+			<data mode="bidirectional" />
+			<input>
+				<port id="0" precision="I64">
+					<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="I64" names="37">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="119" name="aten::to/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="42">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="120" name="Constant_5966" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1, 1" offset="12252628" size="4" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="121" name="aten::rsub/Multiply" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</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">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="122" name="aten::rsub/Subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</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="45,inverted_mask">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="123" name="aten::to/Convert_1" type="Convert" version="opset1">
+			<data destination_type="boolean" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="BOOL" names="50">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="124" name="aten::masked_fill/ConvertLike" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="12252640" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="125" name="aten::masked_fill/Select" type="Select" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32" />
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="52">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="126" name="__module.encoder.layer.0.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="FP32" names="154,attn_output.1">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="127" name="__module.encoder.layer.0.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="12252644" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="128" name="__module.encoder.layer.0.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="155,attn_output.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="129" name="__module.encoder.layer.0.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="130" name="Constant_5468" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="12252660" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="131" name="Constant_5469" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="132" name="Gather_5470" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="133" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Reshape_1_3" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="12252676" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="134" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="156">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="135" name="__module.encoder.layer.0.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="157">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="136" name="self.encoder.layer.0.attention.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="12252684" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="137" name="Convert_6463" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="138" name="self.encoder.layer.0.attention.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="12326412" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="139" name="Convert_6465" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="140" name="self.encoder.layer.0.attention.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="141" name="self.encoder.layer.0.attention.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="12326988" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="142" name="self.encoder.layer.0.attention.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="143" name="Constant_6470" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="144" name="Reshape_6471" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="145" name="self.encoder.layer.0.attention.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="146" name="__module.encoder.layer.0.attention.output.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="147" name="Constant_5968" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12329292" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="148" name="__module.encoder.layer.0.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="163,input.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="149" name="__module.encoder.layer.0.attention.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="165">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="150" name="__module.encoder.layer.0.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="151" name="__module.encoder.layer.0.attention.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="152" name="Constant_5969" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12330828" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="153" name="__module.encoder.layer.0.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="154" name="Constant_5970" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12332364" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="155" name="__module.encoder.layer.0.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="169,input_tensor.1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="156" name="self.encoder.layer.0.intermediate.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 128" offset="12333900" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="157" name="Convert_6287" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="158" name="self.encoder.layer.0.intermediate.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 1" offset="12628812" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="159" name="Convert_6289" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="160" name="self.encoder.layer.0.intermediate.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="161" name="self.encoder.layer.0.intermediate.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 3, 1" offset="12631116" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="162" name="self.encoder.layer.0.intermediate.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="163" name="Constant_6294" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12640332" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="164" name="Reshape_6295" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="165" name="self.encoder.layer.0.intermediate.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="166" name="__module.encoder.layer.0.intermediate.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="167" name="Constant_5971" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="12640340" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="168" name="__module.encoder.layer.0.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="174">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="169" name="__module.encoder.layer.0.intermediate.intermediate_act_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>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="175">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="170" name="self.encoder.layer.0.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 128" offset="12646484" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="171" name="Convert_6298" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="172" name="self.encoder.layer.0.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 1" offset="12941396" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="173" name="Convert_6300" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="174" name="self.encoder.layer.0.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="175" name="self.encoder.layer.0.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 12, 1" offset="12943700" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="176" name="self.encoder.layer.0.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="177" name="Constant_6305" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12952916" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="178" name="Reshape_6306" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="179" name="self.encoder.layer.0.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="180" name="__module.encoder.layer.0.output.dense/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>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="181" name="Constant_5972" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12952924" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="182" name="__module.encoder.layer.0.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="181,input.5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="183" name="__module.encoder.layer.0.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="183">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="184" name="__module.encoder.layer.0.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="185" name="__module.encoder.layer.0.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="186" name="Constant_5973" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12954460" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="187" name="__module.encoder.layer.0.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="188" name="Constant_5974" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="12955996" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="189" name="__module.encoder.layer.0.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="187,hidden_states.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="190" name="self.encoder.layer.1.attention.self.query.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="12957532" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="191" name="Convert_6496" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="192" name="self.encoder.layer.1.attention.self.query.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="13031260" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="193" name="Convert_6498" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="194" name="self.encoder.layer.1.attention.self.query.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="195" name="self.encoder.layer.1.attention.self.query.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="13031836" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="196" name="self.encoder.layer.1.attention.self.query.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="197" name="Constant_6503" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="198" name="Reshape_6504" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="199" name="self.encoder.layer.1.attention.self.query.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="200" name="__module.encoder.layer.1.attention.self.query/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="201" name="Constant_5975" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13034140" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="202" name="__module.encoder.layer.1.attention.self.query/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="200,x.13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="203" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="204" name="__module.encoder.layer.1.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="204,x.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="205" name="Constant_455" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="205">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="206" name="__module.encoder.layer.1.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="206">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="207" name="self.encoder.layer.1.attention.self.key.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="13035676" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="208" name="Convert_6485" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="209" name="self.encoder.layer.1.attention.self.key.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="13109404" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="210" name="Convert_6487" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="211" name="self.encoder.layer.1.attention.self.key.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="212" name="self.encoder.layer.1.attention.self.key.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="13109980" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="213" name="self.encoder.layer.1.attention.self.key.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="214" name="Constant_6492" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="215" name="Reshape_6493" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="216" name="self.encoder.layer.1.attention.self.key.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="217" name="__module.encoder.layer.1.attention.self.key/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="218" name="Constant_5976" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13112284" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="219" name="__module.encoder.layer.1.attention.self.key/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="209,x.17">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="220" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="221" name="__module.encoder.layer.1.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="213,x.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="222" name="Constant_478" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="214">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="223" name="__module.encoder.layer.1.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="215">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="224" name="self.encoder.layer.1.attention.self.value.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="13113820" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="225" name="Convert_6474" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="226" name="self.encoder.layer.1.attention.self.value.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="13187548" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="227" name="Convert_6476" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="228" name="self.encoder.layer.1.attention.self.value.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="229" name="self.encoder.layer.1.attention.self.value.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="13188124" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="230" name="self.encoder.layer.1.attention.self.value.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="231" name="Constant_6481" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="232" name="Reshape_6482" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="233" name="self.encoder.layer.1.attention.self.value.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="234" name="__module.encoder.layer.1.attention.self.value/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="235" name="Constant_5977" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13190428" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="236" name="__module.encoder.layer.1.attention.self.value/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="218,x.21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="237" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="238" name="__module.encoder.layer.1.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="222,x.23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="239" name="Constant_501" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="223">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="240" name="__module.encoder.layer.1.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="224">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="241" name="__module.encoder.layer.1.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="FP32" names="225,attn_output.5">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="242" name="__module.encoder.layer.1.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="12252644" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="243" name="__module.encoder.layer.1.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="226,attn_output.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="244" name="__module.encoder.layer.1.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="245" name="Constant_5488" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="12252660" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="246" name="Constant_5489" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="247" name="Gather_5490" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="248" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="227">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="249" name="__module.encoder.layer.1.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="228">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="250" name="self.encoder.layer.1.attention.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="13191964" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="251" name="Convert_6507" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="252" name="self.encoder.layer.1.attention.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="13265692" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="253" name="Convert_6509" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="254" name="self.encoder.layer.1.attention.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="255" name="self.encoder.layer.1.attention.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="13266268" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="256" name="self.encoder.layer.1.attention.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="257" name="Constant_6514" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="258" name="Reshape_6515" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="259" name="self.encoder.layer.1.attention.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="260" name="__module.encoder.layer.1.attention.output.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="261" name="Constant_5978" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13268572" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="262" name="__module.encoder.layer.1.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="234,input.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="263" name="__module.encoder.layer.1.attention.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="236">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="264" name="__module.encoder.layer.1.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="265" name="__module.encoder.layer.1.attention.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="266" name="Constant_5979" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13270108" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="267" name="__module.encoder.layer.1.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="268" name="Constant_5980" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13271644" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="269" name="__module.encoder.layer.1.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="240,input_tensor.3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="270" name="self.encoder.layer.1.intermediate.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 128" offset="13273180" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="271" name="Convert_6309" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="272" name="self.encoder.layer.1.intermediate.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 1" offset="13568092" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="273" name="Convert_6311" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="274" name="self.encoder.layer.1.intermediate.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="275" name="self.encoder.layer.1.intermediate.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 3, 1" offset="13570396" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="276" name="self.encoder.layer.1.intermediate.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="277" name="Constant_6316" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12640332" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="278" name="Reshape_6317" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="279" name="self.encoder.layer.1.intermediate.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="280" name="__module.encoder.layer.1.intermediate.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="281" name="Constant_5981" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="13579612" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="282" name="__module.encoder.layer.1.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="245">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="283" name="__module.encoder.layer.1.intermediate.intermediate_act_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>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="246">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="284" name="self.encoder.layer.1.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 128" offset="13585756" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="285" name="Convert_6320" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="286" name="self.encoder.layer.1.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 1" offset="13880668" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="287" name="Convert_6322" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="288" name="self.encoder.layer.1.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="289" name="self.encoder.layer.1.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 12, 1" offset="13882972" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="290" name="self.encoder.layer.1.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="291" name="Constant_6327" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12952916" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="292" name="Reshape_6328" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="293" name="self.encoder.layer.1.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="294" name="__module.encoder.layer.1.output.dense/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>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="295" name="Constant_5982" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13892188" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="296" name="__module.encoder.layer.1.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="252,input.9">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="297" name="__module.encoder.layer.1.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="254">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="298" name="__module.encoder.layer.1.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="299" name="__module.encoder.layer.1.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="300" name="Constant_5983" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13893724" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="301" name="__module.encoder.layer.1.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="302" name="Constant_5984" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13895260" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="303" name="__module.encoder.layer.1.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="258,hidden_states.13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="304" name="self.encoder.layer.2.attention.self.query.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="13896796" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="305" name="Convert_6540" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="306" name="self.encoder.layer.2.attention.self.query.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="13970524" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="307" name="Convert_6542" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="308" name="self.encoder.layer.2.attention.self.query.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="309" name="self.encoder.layer.2.attention.self.query.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="13971100" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="310" name="self.encoder.layer.2.attention.self.query.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="311" name="Constant_6547" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="312" name="Reshape_6548" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="313" name="self.encoder.layer.2.attention.self.query.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="314" name="__module.encoder.layer.2.attention.self.query/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="315" name="Constant_5985" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="13973404" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="316" name="__module.encoder.layer.2.attention.self.query/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="271,x.25">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="317" name="__module.encoder.layer.2.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="318" name="__module.encoder.layer.2.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="275,x.27">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="319" name="Constant_657" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="276">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="320" name="__module.encoder.layer.2.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="277">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="321" name="self.encoder.layer.2.attention.self.key.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="13974940" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="322" name="Convert_6529" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="323" name="self.encoder.layer.2.attention.self.key.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="14048668" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="324" name="Convert_6531" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="325" name="self.encoder.layer.2.attention.self.key.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="326" name="self.encoder.layer.2.attention.self.key.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="14049244" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="327" name="self.encoder.layer.2.attention.self.key.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="328" name="Constant_6536" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="329" name="Reshape_6537" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="330" name="self.encoder.layer.2.attention.self.key.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="331" name="__module.encoder.layer.2.attention.self.key/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="332" name="Constant_5986" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14051548" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="333" name="__module.encoder.layer.2.attention.self.key/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="280,x.29">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="334" name="__module.encoder.layer.2.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="335" name="__module.encoder.layer.2.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="284,x.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="336" name="Constant_680" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="285">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="337" name="__module.encoder.layer.2.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="286">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="338" name="self.encoder.layer.2.attention.self.value.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="14053084" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="339" name="Convert_6518" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="340" name="self.encoder.layer.2.attention.self.value.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="14126812" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="341" name="Convert_6520" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="342" name="self.encoder.layer.2.attention.self.value.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="343" name="self.encoder.layer.2.attention.self.value.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="14127388" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="344" name="self.encoder.layer.2.attention.self.value.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="345" name="Constant_6525" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="346" name="Reshape_6526" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="347" name="self.encoder.layer.2.attention.self.value.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="348" name="__module.encoder.layer.2.attention.self.value/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="349" name="Constant_5987" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14129692" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="350" name="__module.encoder.layer.2.attention.self.value/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="289,x.33">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="351" name="__module.encoder.layer.2.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="352" name="__module.encoder.layer.2.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="293,x.35">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="353" name="Constant_703" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="294">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="354" name="__module.encoder.layer.2.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="295">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="355" name="__module.encoder.layer.2.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="FP32" names="296,attn_output.9">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="356" name="__module.encoder.layer.2.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="12252644" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="357" name="__module.encoder.layer.2.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="297,attn_output.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="358" name="__module.encoder.layer.2.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="359" name="Constant_5508" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="12252660" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="360" name="Constant_5509" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="361" name="Gather_5510" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="362" name="__module.encoder.layer.2.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="298">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="363" name="__module.encoder.layer.2.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="299">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="364" name="self.encoder.layer.2.attention.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="14131228" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="365" name="Convert_6551" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="366" name="self.encoder.layer.2.attention.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="14204956" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="367" name="Convert_6553" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="368" name="self.encoder.layer.2.attention.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="369" name="self.encoder.layer.2.attention.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="14205532" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="370" name="self.encoder.layer.2.attention.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="371" name="Constant_6558" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="372" name="Reshape_6559" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="373" name="self.encoder.layer.2.attention.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="374" name="__module.encoder.layer.2.attention.output.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="375" name="Constant_5988" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14207836" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="376" name="__module.encoder.layer.2.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="305,input.11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="377" name="__module.encoder.layer.2.attention.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="307">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="378" name="__module.encoder.layer.2.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="379" name="__module.encoder.layer.2.attention.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="380" name="Constant_5989" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14209372" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="381" name="__module.encoder.layer.2.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="382" name="Constant_5990" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14210908" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="383" name="__module.encoder.layer.2.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="311,input_tensor.5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="384" name="self.encoder.layer.2.intermediate.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 128" offset="14212444" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="385" name="Convert_6331" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="386" name="self.encoder.layer.2.intermediate.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 1" offset="14507356" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="387" name="Convert_6333" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="388" name="self.encoder.layer.2.intermediate.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="389" name="self.encoder.layer.2.intermediate.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 3, 1" offset="14509660" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="390" name="self.encoder.layer.2.intermediate.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="391" name="Constant_6338" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12640332" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="392" name="Reshape_6339" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="393" name="self.encoder.layer.2.intermediate.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="394" name="__module.encoder.layer.2.intermediate.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="395" name="Constant_5991" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="14518876" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="396" name="__module.encoder.layer.2.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="316">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="397" name="__module.encoder.layer.2.intermediate.intermediate_act_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>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="317">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="398" name="self.encoder.layer.2.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 128" offset="14525020" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="399" name="Convert_6342" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="400" name="self.encoder.layer.2.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 1" offset="14819932" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="401" name="Convert_6344" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="402" name="self.encoder.layer.2.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="403" name="self.encoder.layer.2.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 12, 1" offset="14822236" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="404" name="self.encoder.layer.2.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="405" name="Constant_6349" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12952916" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="406" name="Reshape_6350" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="407" name="self.encoder.layer.2.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="408" name="__module.encoder.layer.2.output.dense/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>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="409" name="Constant_5992" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14831452" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="410" name="__module.encoder.layer.2.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="323,input.13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="411" name="__module.encoder.layer.2.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="325">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="412" name="__module.encoder.layer.2.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="413" name="__module.encoder.layer.2.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="414" name="Constant_5993" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14832988" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="415" name="__module.encoder.layer.2.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="416" name="Constant_5994" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14834524" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="417" name="__module.encoder.layer.2.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="329,hidden_states.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="418" name="self.encoder.layer.3.attention.self.query.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="14836060" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="419" name="Convert_6584" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="420" name="self.encoder.layer.3.attention.self.query.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="14909788" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="421" name="Convert_6586" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="422" name="self.encoder.layer.3.attention.self.query.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="423" name="self.encoder.layer.3.attention.self.query.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="14910364" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="424" name="self.encoder.layer.3.attention.self.query.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="425" name="Constant_6591" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="426" name="Reshape_6592" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="427" name="self.encoder.layer.3.attention.self.query.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="428" name="__module.encoder.layer.3.attention.self.query/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="429" name="Constant_5995" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14912668" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="430" name="__module.encoder.layer.3.attention.self.query/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="342,x.37">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="431" name="__module.encoder.layer.3.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="432" name="__module.encoder.layer.3.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="346,x.39">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="433" name="Constant_859" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="347">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="434" name="__module.encoder.layer.3.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="348">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="435" name="self.encoder.layer.3.attention.self.key.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="14914204" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="436" name="Convert_6573" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="437" name="self.encoder.layer.3.attention.self.key.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="14987932" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="438" name="Convert_6575" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="439" name="self.encoder.layer.3.attention.self.key.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="440" name="self.encoder.layer.3.attention.self.key.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="14988508" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="441" name="self.encoder.layer.3.attention.self.key.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="442" name="Constant_6580" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="443" name="Reshape_6581" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="444" name="self.encoder.layer.3.attention.self.key.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="445" name="__module.encoder.layer.3.attention.self.key/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="446" name="Constant_5996" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="14990812" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="447" name="__module.encoder.layer.3.attention.self.key/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="351,x.41">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="448" name="__module.encoder.layer.3.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="449" name="__module.encoder.layer.3.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="355,x.43">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="450" name="Constant_882" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="356">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="451" name="__module.encoder.layer.3.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="357">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="452" name="self.encoder.layer.3.attention.self.value.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="14992348" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="453" name="Convert_6562" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="454" name="self.encoder.layer.3.attention.self.value.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="15066076" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="455" name="Convert_6564" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="456" name="self.encoder.layer.3.attention.self.value.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="457" name="self.encoder.layer.3.attention.self.value.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="15066652" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="458" name="self.encoder.layer.3.attention.self.value.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="459" name="Constant_6569" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="460" name="Reshape_6570" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="461" name="self.encoder.layer.3.attention.self.value.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="462" name="__module.encoder.layer.3.attention.self.value/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="463" name="Constant_5997" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15068956" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="464" name="__module.encoder.layer.3.attention.self.value/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="360,x.45">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="465" name="__module.encoder.layer.3.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="466" name="__module.encoder.layer.3.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="364,x.47">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="467" name="Constant_905" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="365">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="468" name="__module.encoder.layer.3.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="366">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="469" name="__module.encoder.layer.3.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="FP32" names="367,attn_output.13">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="470" name="__module.encoder.layer.3.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="12252644" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="471" name="__module.encoder.layer.3.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="368,attn_output.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="472" name="__module.encoder.layer.3.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="473" name="Constant_5528" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="12252660" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="474" name="Constant_5529" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="475" name="Gather_5530" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="476" name="__module.encoder.layer.3.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="369">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="477" name="__module.encoder.layer.3.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="370">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="478" name="self.encoder.layer.3.attention.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="15070492" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="479" name="Convert_6595" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="480" name="self.encoder.layer.3.attention.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="15144220" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="481" name="Convert_6597" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="482" name="self.encoder.layer.3.attention.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="483" name="self.encoder.layer.3.attention.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="15144796" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="484" name="self.encoder.layer.3.attention.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="485" name="Constant_6602" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="486" name="Reshape_6603" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="487" name="self.encoder.layer.3.attention.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="488" name="__module.encoder.layer.3.attention.output.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="489" name="Constant_5998" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15147100" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="490" name="__module.encoder.layer.3.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="376,input.15">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="491" name="__module.encoder.layer.3.attention.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="378">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="492" name="__module.encoder.layer.3.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="493" name="__module.encoder.layer.3.attention.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="494" name="Constant_5999" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15148636" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="495" name="__module.encoder.layer.3.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="496" name="Constant_6000" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15150172" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="497" name="__module.encoder.layer.3.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="382,input_tensor.7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="498" name="self.encoder.layer.3.intermediate.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 128" offset="15151708" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="499" name="Convert_6353" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="500" name="self.encoder.layer.3.intermediate.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 1" offset="15446620" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="501" name="Convert_6355" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="502" name="self.encoder.layer.3.intermediate.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="503" name="self.encoder.layer.3.intermediate.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 3, 1" offset="15448924" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="504" name="self.encoder.layer.3.intermediate.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="505" name="Constant_6360" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12640332" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="506" name="Reshape_6361" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="507" name="self.encoder.layer.3.intermediate.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="508" name="__module.encoder.layer.3.intermediate.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="509" name="Constant_6001" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="15458140" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="510" name="__module.encoder.layer.3.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="387">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="511" name="__module.encoder.layer.3.intermediate.intermediate_act_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>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="388">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="512" name="self.encoder.layer.3.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 128" offset="15464284" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="513" name="Convert_6364" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="514" name="self.encoder.layer.3.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 1" offset="15759196" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="515" name="Convert_6366" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="516" name="self.encoder.layer.3.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="517" name="self.encoder.layer.3.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 12, 1" offset="15761500" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="518" name="self.encoder.layer.3.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="519" name="Constant_6371" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12952916" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="520" name="Reshape_6372" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="521" name="self.encoder.layer.3.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="522" name="__module.encoder.layer.3.output.dense/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>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="523" name="Constant_6002" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15770716" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="524" name="__module.encoder.layer.3.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="394,input.17">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="525" name="__module.encoder.layer.3.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="396">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="526" name="__module.encoder.layer.3.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="527" name="__module.encoder.layer.3.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="528" name="Constant_6003" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15772252" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="529" name="__module.encoder.layer.3.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="530" name="Constant_6004" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15773788" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="531" name="__module.encoder.layer.3.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="400,hidden_states.25">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="532" name="self.encoder.layer.4.attention.self.query.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="15775324" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="533" name="Convert_6628" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="534" name="self.encoder.layer.4.attention.self.query.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="15849052" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="535" name="Convert_6630" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="536" name="self.encoder.layer.4.attention.self.query.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="537" name="self.encoder.layer.4.attention.self.query.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="15849628" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="538" name="self.encoder.layer.4.attention.self.query.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="539" name="Constant_6635" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="540" name="Reshape_6636" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="541" name="self.encoder.layer.4.attention.self.query.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="542" name="__module.encoder.layer.4.attention.self.query/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="543" name="Constant_6005" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15851932" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="544" name="__module.encoder.layer.4.attention.self.query/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="413,x.49">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="545" name="__module.encoder.layer.4.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="546" name="__module.encoder.layer.4.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="417,x.51">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="547" name="Constant_1061" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="418">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="548" name="__module.encoder.layer.4.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="419">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="549" name="self.encoder.layer.4.attention.self.key.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="15853468" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="550" name="Convert_6617" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="551" name="self.encoder.layer.4.attention.self.key.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="15927196" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="552" name="Convert_6619" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="553" name="self.encoder.layer.4.attention.self.key.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="554" name="self.encoder.layer.4.attention.self.key.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="15927772" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="555" name="self.encoder.layer.4.attention.self.key.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="556" name="Constant_6624" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="557" name="Reshape_6625" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="558" name="self.encoder.layer.4.attention.self.key.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="559" name="__module.encoder.layer.4.attention.self.key/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="560" name="Constant_6006" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="15930076" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="561" name="__module.encoder.layer.4.attention.self.key/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="422,x.53">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="562" name="__module.encoder.layer.4.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="563" name="__module.encoder.layer.4.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="426,x.55">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="564" name="Constant_1084" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="427">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="565" name="__module.encoder.layer.4.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="428">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="566" name="self.encoder.layer.4.attention.self.value.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="15931612" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="567" name="Convert_6606" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="568" name="self.encoder.layer.4.attention.self.value.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="16005340" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="569" name="Convert_6608" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="570" name="self.encoder.layer.4.attention.self.value.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="571" name="self.encoder.layer.4.attention.self.value.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="16005916" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="572" name="self.encoder.layer.4.attention.self.value.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="573" name="Constant_6613" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="574" name="Reshape_6614" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="575" name="self.encoder.layer.4.attention.self.value.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="576" name="__module.encoder.layer.4.attention.self.value/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="577" name="Constant_6007" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16008220" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="578" name="__module.encoder.layer.4.attention.self.value/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="431,x.57">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="579" name="__module.encoder.layer.4.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="580" name="__module.encoder.layer.4.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="435,x.59">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="581" name="Constant_1107" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="436">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="582" name="__module.encoder.layer.4.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="437">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="583" name="__module.encoder.layer.4.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="FP32" names="438,attn_output.17">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="584" name="__module.encoder.layer.4.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="12252644" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="585" name="__module.encoder.layer.4.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="439,attn_output.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="586" name="__module.encoder.layer.4.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="587" name="Constant_5548" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="12252660" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="588" name="Constant_5549" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="589" name="Gather_5550" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="590" name="__module.encoder.layer.4.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="440">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="591" name="__module.encoder.layer.4.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="441">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="592" name="self.encoder.layer.4.attention.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="16009756" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="593" name="Convert_6639" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="594" name="self.encoder.layer.4.attention.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="16083484" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="595" name="Convert_6641" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="596" name="self.encoder.layer.4.attention.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="597" name="self.encoder.layer.4.attention.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="16084060" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="598" name="self.encoder.layer.4.attention.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="599" name="Constant_6646" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="600" name="Reshape_6647" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="601" name="self.encoder.layer.4.attention.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="602" name="__module.encoder.layer.4.attention.output.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="603" name="Constant_6008" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16086364" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="604" name="__module.encoder.layer.4.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="447,input.19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="605" name="__module.encoder.layer.4.attention.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="449">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="606" name="__module.encoder.layer.4.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="607" name="__module.encoder.layer.4.attention.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="608" name="Constant_6009" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16087900" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="609" name="__module.encoder.layer.4.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="610" name="Constant_6010" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16089436" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="611" name="__module.encoder.layer.4.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="453,input_tensor.9">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="612" name="self.encoder.layer.4.intermediate.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 128" offset="16090972" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="613" name="Convert_6375" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="614" name="self.encoder.layer.4.intermediate.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 1" offset="16385884" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="615" name="Convert_6377" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="616" name="self.encoder.layer.4.intermediate.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="617" name="self.encoder.layer.4.intermediate.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 3, 1" offset="16388188" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="618" name="self.encoder.layer.4.intermediate.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="619" name="Constant_6382" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12640332" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="620" name="Reshape_6383" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="621" name="self.encoder.layer.4.intermediate.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="622" name="__module.encoder.layer.4.intermediate.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="623" name="Constant_6011" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="16397404" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="624" name="__module.encoder.layer.4.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="458">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="625" name="__module.encoder.layer.4.intermediate.intermediate_act_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>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="459">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="626" name="self.encoder.layer.4.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 128" offset="16403548" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="627" name="Convert_6386" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="628" name="self.encoder.layer.4.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 12, 1" offset="16698460" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="629" name="Convert_6388" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="630" name="self.encoder.layer.4.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="631" name="self.encoder.layer.4.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 12, 1" offset="16700764" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="632" name="self.encoder.layer.4.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="633" name="Constant_6393" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12952916" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="634" name="Reshape_6394" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>12</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="635" name="self.encoder.layer.4.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="636" name="__module.encoder.layer.4.output.dense/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>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="637" name="Constant_6012" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16709980" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="638" name="__module.encoder.layer.4.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="465,input.21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="639" name="__module.encoder.layer.4.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="467">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="640" name="__module.encoder.layer.4.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="641" name="__module.encoder.layer.4.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="642" name="Constant_6013" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16711516" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="643" name="__module.encoder.layer.4.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="644" name="Constant_6014" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16713052" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="645" name="__module.encoder.layer.4.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="471,hidden_states.31">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="646" name="self.encoder.layer.5.attention.self.query.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="16714588" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="647" name="Convert_6672" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="648" name="self.encoder.layer.5.attention.self.query.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="16788316" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="649" name="Convert_6674" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="650" name="self.encoder.layer.5.attention.self.query.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="651" name="self.encoder.layer.5.attention.self.query.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="16788892" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="652" name="self.encoder.layer.5.attention.self.query.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="653" name="Constant_6679" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="654" name="Reshape_6680" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="655" name="self.encoder.layer.5.attention.self.query.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="656" name="__module.encoder.layer.5.attention.self.query/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="657" name="Constant_6015" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16791196" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="658" name="__module.encoder.layer.5.attention.self.query/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="484,x.61">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="659" name="__module.encoder.layer.5.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="660" name="__module.encoder.layer.5.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="488,x.63">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="661" name="Constant_1263" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="489">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="662" name="__module.encoder.layer.5.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="490">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="663" name="self.encoder.layer.5.attention.self.key.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="16792732" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="664" name="Convert_6661" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="665" name="self.encoder.layer.5.attention.self.key.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="16866460" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="666" name="Convert_6663" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="667" name="self.encoder.layer.5.attention.self.key.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="668" name="self.encoder.layer.5.attention.self.key.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="16867036" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="669" name="self.encoder.layer.5.attention.self.key.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="670" name="Constant_6668" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="671" name="Reshape_6669" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="672" name="self.encoder.layer.5.attention.self.key.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="673" name="__module.encoder.layer.5.attention.self.key/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="674" name="Constant_6016" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16869340" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="675" name="__module.encoder.layer.5.attention.self.key/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="493,x.65">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="676" name="__module.encoder.layer.5.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="677" name="__module.encoder.layer.5.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="497,x.67">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="678" name="Constant_1286" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="498">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="679" name="__module.encoder.layer.5.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="499">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="680" name="self.encoder.layer.5.attention.self.value.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="16870876" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="681" name="Convert_6650" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="682" name="self.encoder.layer.5.attention.self.value.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="16944604" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="683" name="Convert_6652" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="684" name="self.encoder.layer.5.attention.self.value.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="685" name="self.encoder.layer.5.attention.self.value.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="16945180" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="686" name="self.encoder.layer.5.attention.self.value.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="687" name="Constant_6657" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="688" name="Reshape_6658" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="689" name="self.encoder.layer.5.attention.self.value.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="690" name="__module.encoder.layer.5.attention.self.value/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="691" name="Constant_6017" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="16947484" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="692" name="__module.encoder.layer.5.attention.self.value/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="502,x.69">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="693" name="__module.encoder.layer.5.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096276" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="694" name="__module.encoder.layer.5.attention.self/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>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="506,x">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="695" name="Constant_1309" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="12096308" size="32" />
+			<output>
+				<port id="0" precision="I64" names="507">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="696" name="__module.encoder.layer.5.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="508">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="697" name="__module.encoder.layer.5.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="FP32" names="509,attn_output.21">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="698" name="__module.encoder.layer.5.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="12252644" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="699" name="__module.encoder.layer.5.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>-1</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="510,attn_output">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="700" name="__module.encoder.layer.5.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="701" name="Constant_5568" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="12252660" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="702" name="Constant_5569" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="12015032" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="703" name="Gather_5570" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="704" name="__module.encoder.layer.5.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="511">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="705" name="__module.encoder.layer.5.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>12</dim>
+					<dim>32</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="512">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="706" name="self.encoder.layer.5.attention.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 128" offset="16949020" size="73728" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="707" name="Convert_6683" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="708" name="self.encoder.layer.5.attention.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="384, 3, 1" offset="17022748" size="576" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="709" name="Convert_6685" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="710" name="self.encoder.layer.5.attention.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="711" name="self.encoder.layer.5.attention.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 3, 1" offset="17023324" size="2304" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="712" name="self.encoder.layer.5.attention.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="713" name="Constant_6690" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12094732" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="714" name="Reshape_6691" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="715" name="self.encoder.layer.5.attention.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="716" name="__module.encoder.layer.5.attention.output.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="717" name="Constant_6018" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="17025628" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="718" name="__module.encoder.layer.5.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="518,input.23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="719" name="__module.encoder.layer.5.attention.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="520">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="720" name="__module.encoder.layer.5.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="721" name="__module.encoder.layer.5.attention.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="722" name="Constant_6019" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="17027164" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="723" name="__module.encoder.layer.5.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="724" name="Constant_6020" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="17028700" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="725" name="__module.encoder.layer.5.attention.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="524,input_tensor">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="726" name="self.encoder.layer.5.intermediate.dense.weight" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 128" offset="17030236" size="294912" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="727" name="Convert_6397" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="728" name="self.encoder.layer.5.intermediate.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u4" shape="1536, 3, 1" offset="17325148" size="2304" />
+			<output>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="729" name="Convert_6399" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U4">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="730" name="self.encoder.layer.5.intermediate.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="731" name="self.encoder.layer.5.intermediate.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 3, 1" offset="17327452" size="9216" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="732" name="self.encoder.layer.5.intermediate.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="733" name="Constant_6404" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="12640332" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="734" name="Reshape_6405" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>3</dim>
+					<dim>128</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="735" name="self.encoder.layer.5.intermediate.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="736" name="__module.encoder.layer.5.intermediate.dense/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="737" name="Constant_6021" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="17336668" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="738" name="__module.encoder.layer.5.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="529">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="739" name="__module.encoder.layer.5.intermediate.intermediate_act_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>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="530">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="740" name="self.encoder.layer.5.output.dense.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1536" offset="17342812" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="741" name="Convert_6409" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="742" name="self.encoder.layer.5.output.dense.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="17932636" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="743" name="Convert_6412" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="744" name="self.encoder.layer.5.output.dense.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="745" name="self.encoder.layer.5.output.dense.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="17933020" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="746" name="self.encoder.layer.5.output.dense.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="747" name="self.encoder.layer.5.output.dense.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="748" name="__module.encoder.layer.5.output.dense/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>1536</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="749" name="Constant_6022" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="17933788" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="750" name="__module.encoder.layer.5.output.dense/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="536,input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="751" name="__module.encoder.layer.5.output/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="538">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="752" name="__module.encoder.layer.5.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="12015048" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="753" name="__module.encoder.layer.5.output.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="754" name="Constant_6023" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="17935324" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="755" name="__module.encoder.layer.5.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="756" name="Constant_6024" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="17936860" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="757" name="__module.encoder.layer.5.output.LayerNorm/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>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="last_hidden_state">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="758" name="Result_2422" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="22" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="109" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="106" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="11" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="36" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
+		<edge from-layer="4" from-port="1" to-layer="7" to-port="0" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
+		<edge from-layer="7" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="8" from-port="0" to-layer="9" to-port="1" />
+		<edge from-layer="9" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="10" from-port="1" to-layer="13" to-port="0" />
+		<edge from-layer="11" from-port="1" to-layer="13" to-port="1" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
+		<edge from-layer="13" from-port="3" to-layer="25" to-port="0" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="18" to-port="0" />
+		<edge from-layer="16" from-port="0" to-layer="17" to-port="0" />
+		<edge from-layer="17" from-port="1" to-layer="18" to-port="1" />
+		<edge from-layer="18" from-port="2" to-layer="20" to-port="0" />
+		<edge from-layer="19" from-port="0" to-layer="20" to-port="1" />
+		<edge from-layer="20" from-port="2" to-layer="21" to-port="0" />
+		<edge from-layer="21" from-port="1" to-layer="24" to-port="0" />
+		<edge from-layer="22" from-port="1" to-layer="24" to-port="1" />
+		<edge from-layer="23" from-port="0" to-layer="24" to-port="2" />
+		<edge from-layer="24" from-port="3" to-layer="25" to-port="1" />
+		<edge from-layer="25" from-port="2" to-layer="46" to-port="0" />
+		<edge from-layer="26" from-port="0" to-layer="27" to-port="0" />
+		<edge from-layer="27" from-port="1" to-layer="30" to-port="0" />
+		<edge from-layer="28" from-port="0" to-layer="29" to-port="0" />
+		<edge from-layer="29" from-port="1" to-layer="30" to-port="1" />
+		<edge from-layer="30" from-port="2" to-layer="32" to-port="0" />
+		<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
+		<edge from-layer="32" from-port="2" to-layer="33" to-port="0" />
+		<edge from-layer="33" from-port="1" to-layer="45" to-port="0" />
+		<edge from-layer="34" from-port="0" to-layer="42" to-port="0" />
+		<edge from-layer="35" from-port="0" to-layer="42" to-port="1" />
+		<edge from-layer="36" from-port="1" to-layer="39" to-port="0" />
+		<edge from-layer="37" from-port="0" to-layer="39" to-port="1" />
+		<edge from-layer="38" from-port="0" to-layer="39" to-port="2" />
+		<edge from-layer="39" from-port="3" to-layer="42" to-port="2" />
+		<edge from-layer="39" from-port="3" to-layer="117" to-port="2" />
+		<edge from-layer="40" from-port="0" to-layer="42" to-port="3" />
+		<edge from-layer="41" from-port="0" to-layer="42" to-port="4" />
+		<edge from-layer="42" from-port="5" to-layer="43" to-port="0" />
+		<edge from-layer="43" from-port="1" to-layer="45" to-port="1" />
+		<edge from-layer="44" from-port="0" to-layer="45" to-port="2" />
+		<edge from-layer="45" from-port="3" to-layer="46" to-port="1" />
+		<edge from-layer="46" from-port="2" to-layer="48" to-port="0" />
+		<edge from-layer="47" from-port="0" to-layer="48" to-port="1" />
+		<edge from-layer="48" from-port="2" to-layer="50" to-port="0" />
+		<edge from-layer="49" from-port="0" to-layer="50" to-port="1" />
+		<edge from-layer="50" from-port="2" to-layer="52" to-port="0" />
+		<edge from-layer="51" from-port="0" to-layer="52" to-port="1" />
+		<edge from-layer="52" from-port="2" to-layer="63" to-port="0" />
+		<edge from-layer="52" from-port="2" to-layer="149" to-port="1" />
+		<edge from-layer="52" from-port="2" to-layer="97" to-port="0" />
+		<edge from-layer="52" from-port="2" to-layer="80" to-port="0" />
+		<edge from-layer="52" from-port="2" to-layer="129" to-port="0" />
+		<edge from-layer="53" from-port="0" to-layer="54" to-port="0" />
+		<edge from-layer="54" from-port="1" to-layer="57" to-port="0" />
+		<edge from-layer="55" from-port="0" to-layer="56" to-port="0" />
+		<edge from-layer="56" from-port="1" to-layer="57" to-port="1" />
+		<edge from-layer="57" from-port="2" to-layer="59" to-port="0" />
+		<edge from-layer="58" from-port="0" to-layer="59" to-port="1" />
+		<edge from-layer="59" from-port="2" to-layer="61" to-port="0" />
+		<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
+		<edge from-layer="61" from-port="2" to-layer="62" to-port="0" />
+		<edge from-layer="62" from-port="1" to-layer="63" to-port="1" />
+		<edge from-layer="63" from-port="2" to-layer="65" to-port="0" />
+		<edge from-layer="64" from-port="0" to-layer="65" to-port="1" />
+		<edge from-layer="65" from-port="2" to-layer="67" to-port="0" />
+		<edge from-layer="66" from-port="0" to-layer="67" to-port="1" />
+		<edge from-layer="67" from-port="2" to-layer="69" to-port="0" />
+		<edge from-layer="68" from-port="0" to-layer="69" to-port="1" />
+		<edge from-layer="69" from-port="2" to-layer="126" to-port="0" />
+		<edge from-layer="70" from-port="0" to-layer="71" to-port="0" />
+		<edge from-layer="71" from-port="1" to-layer="74" to-port="0" />
+		<edge from-layer="72" from-port="0" to-layer="73" to-port="0" />
+		<edge from-layer="73" from-port="1" to-layer="74" to-port="1" />
+		<edge from-layer="74" from-port="2" to-layer="76" to-port="0" />
+		<edge from-layer="75" from-port="0" to-layer="76" to-port="1" />
+		<edge from-layer="76" from-port="2" to-layer="78" to-port="0" />
+		<edge from-layer="77" from-port="0" to-layer="78" to-port="1" />
+		<edge from-layer="78" from-port="2" to-layer="79" to-port="0" />
+		<edge from-layer="79" from-port="1" to-layer="80" to-port="1" />
+		<edge from-layer="80" from-port="2" to-layer="82" to-port="0" />
+		<edge from-layer="81" from-port="0" to-layer="82" to-port="1" />
+		<edge from-layer="82" from-port="2" to-layer="84" to-port="0" />
+		<edge from-layer="83" from-port="0" to-layer="84" to-port="1" />
+		<edge from-layer="84" from-port="2" to-layer="86" to-port="0" />
+		<edge from-layer="85" from-port="0" to-layer="86" to-port="1" />
+		<edge from-layer="86" from-port="2" to-layer="126" to-port="1" />
+		<edge from-layer="87" from-port="0" to-layer="88" to-port="0" />
+		<edge from-layer="88" from-port="1" to-layer="91" to-port="0" />
+		<edge from-layer="89" from-port="0" to-layer="90" to-port="0" />
+		<edge from-layer="90" from-port="1" to-layer="91" to-port="1" />
+		<edge from-layer="91" from-port="2" to-layer="93" to-port="0" />
+		<edge from-layer="92" from-port="0" to-layer="93" to-port="1" />
+		<edge from-layer="93" from-port="2" to-layer="95" to-port="0" />
+		<edge from-layer="94" from-port="0" to-layer="95" to-port="1" />
+		<edge from-layer="95" from-port="2" to-layer="96" to-port="0" />
+		<edge from-layer="96" from-port="1" to-layer="97" to-port="1" />
+		<edge from-layer="97" from-port="2" to-layer="99" to-port="0" />
+		<edge from-layer="98" from-port="0" to-layer="99" to-port="1" />
+		<edge from-layer="99" from-port="2" to-layer="101" to-port="0" />
+		<edge from-layer="100" from-port="0" to-layer="101" to-port="1" />
+		<edge from-layer="101" from-port="2" to-layer="103" to-port="0" />
+		<edge from-layer="102" from-port="0" to-layer="103" to-port="1" />
+		<edge from-layer="103" from-port="2" to-layer="126" to-port="2" />
+		<edge from-layer="104" from-port="0" to-layer="122" to-port="0" />
+		<edge from-layer="105" from-port="0" to-layer="106" to-port="1" />
+		<edge from-layer="106" from-port="2" to-layer="108" to-port="0" />
+		<edge from-layer="107" from-port="0" to-layer="108" to-port="1" />
+		<edge from-layer="108" from-port="2" to-layer="118" to-port="0" />
+		<edge from-layer="109" from-port="1" to-layer="116" to-port="0" />
+		<edge from-layer="109" from-port="1" to-layer="112" to-port="0" />
+		<edge from-layer="110" from-port="0" to-layer="112" to-port="1" />
+		<edge from-layer="111" from-port="0" to-layer="112" to-port="2" />
+		<edge from-layer="112" from-port="3" to-layer="117" to-port="0" />
+		<edge from-layer="113" from-port="0" to-layer="117" to-port="1" />
+		<edge from-layer="114" from-port="0" to-layer="116" to-port="1" />
+		<edge from-layer="115" from-port="0" to-layer="116" to-port="2" />
+		<edge from-layer="116" from-port="3" to-layer="117" to-port="3" />
+		<edge from-layer="117" from-port="4" to-layer="118" to-port="1" />
+		<edge from-layer="118" from-port="2" to-layer="119" to-port="0" />
+		<edge from-layer="119" from-port="1" to-layer="121" to-port="0" />
+		<edge from-layer="120" from-port="0" to-layer="121" to-port="1" />
+		<edge from-layer="121" from-port="2" to-layer="122" to-port="1" />
+		<edge from-layer="122" from-port="2" to-layer="123" to-port="0" />
+		<edge from-layer="122" from-port="2" to-layer="125" to-port="2" />
+		<edge from-layer="123" from-port="1" to-layer="125" to-port="0" />
+		<edge from-layer="124" from-port="0" to-layer="125" to-port="1" />
+		<edge from-layer="125" from-port="3" to-layer="126" to-port="3" />
+		<edge from-layer="125" from-port="3" to-layer="355" to-port="3" />
+		<edge from-layer="125" from-port="3" to-layer="241" to-port="3" />
+		<edge from-layer="125" from-port="3" to-layer="697" to-port="3" />
+		<edge from-layer="125" from-port="3" to-layer="583" to-port="3" />
+		<edge from-layer="125" from-port="3" to-layer="469" to-port="3" />
+		<edge from-layer="126" from-port="4" to-layer="128" to-port="0" />
+		<edge from-layer="127" from-port="0" to-layer="128" to-port="1" />
+		<edge from-layer="128" from-port="2" to-layer="135" to-port="0" />
+		<edge from-layer="129" from-port="1" to-layer="132" to-port="0" />
+		<edge from-layer="130" from-port="0" to-layer="132" to-port="1" />
+		<edge from-layer="131" from-port="0" to-layer="132" to-port="2" />
+		<edge from-layer="132" from-port="3" to-layer="134" to-port="0" />
+		<edge from-layer="133" from-port="0" to-layer="134" to-port="1" />
+		<edge from-layer="133" from-port="0" to-layer="362" to-port="1" />
+		<edge from-layer="133" from-port="0" to-layer="704" to-port="1" />
+		<edge from-layer="133" from-port="0" to-layer="248" to-port="1" />
+		<edge from-layer="133" from-port="0" to-layer="590" to-port="1" />
+		<edge from-layer="133" from-port="0" to-layer="476" to-port="1" />
+		<edge from-layer="134" from-port="2" to-layer="135" to-port="1" />
+		<edge from-layer="135" from-port="2" to-layer="146" to-port="0" />
+		<edge from-layer="136" from-port="0" to-layer="137" to-port="0" />
+		<edge from-layer="137" from-port="1" to-layer="140" to-port="0" />
+		<edge from-layer="138" from-port="0" 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="145" to-port="0" />
+		<edge from-layer="145" from-port="1" to-layer="146" to-port="1" />
+		<edge from-layer="146" from-port="2" to-layer="148" to-port="0" />
+		<edge from-layer="147" from-port="0" to-layer="148" to-port="1" />
+		<edge from-layer="148" from-port="2" to-layer="149" to-port="0" />
+		<edge from-layer="149" from-port="2" to-layer="151" to-port="0" />
+		<edge from-layer="150" from-port="0" to-layer="151" to-port="1" />
+		<edge from-layer="151" from-port="2" to-layer="153" to-port="0" />
+		<edge from-layer="152" from-port="0" to-layer="153" to-port="1" />
+		<edge from-layer="153" from-port="2" to-layer="155" to-port="0" />
+		<edge from-layer="154" from-port="0" to-layer="155" to-port="1" />
+		<edge from-layer="155" from-port="2" to-layer="166" to-port="0" />
+		<edge from-layer="155" from-port="2" to-layer="183" to-port="1" />
+		<edge from-layer="156" from-port="0" to-layer="157" to-port="0" />
+		<edge from-layer="157" from-port="1" to-layer="160" to-port="0" />
+		<edge from-layer="158" from-port="0" to-layer="159" to-port="0" />
+		<edge from-layer="159" from-port="1" to-layer="160" to-port="1" />
+		<edge from-layer="160" from-port="2" to-layer="162" to-port="0" />
+		<edge from-layer="161" from-port="0" 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="0" />
+		<edge from-layer="165" from-port="1" to-layer="166" to-port="1" />
+		<edge from-layer="166" from-port="2" to-layer="168" to-port="0" />
+		<edge from-layer="167" from-port="0" to-layer="168" to-port="1" />
+		<edge from-layer="168" from-port="2" to-layer="169" to-port="0" />
+		<edge from-layer="169" from-port="1" to-layer="180" to-port="0" />
+		<edge from-layer="170" from-port="0" to-layer="171" to-port="0" />
+		<edge from-layer="171" from-port="1" to-layer="174" 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="174" to-port="1" />
+		<edge from-layer="174" from-port="2" to-layer="176" to-port="0" />
+		<edge from-layer="175" from-port="0" 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="179" to-port="0" />
+		<edge from-layer="179" from-port="1" to-layer="180" to-port="1" />
+		<edge from-layer="180" from-port="2" to-layer="182" to-port="0" />
+		<edge from-layer="181" from-port="0" to-layer="182" to-port="1" />
+		<edge from-layer="182" from-port="2" to-layer="183" to-port="0" />
+		<edge from-layer="183" from-port="2" to-layer="185" to-port="0" />
+		<edge from-layer="184" from-port="0" to-layer="185" to-port="1" />
+		<edge from-layer="185" from-port="2" to-layer="187" to-port="0" />
+		<edge from-layer="186" from-port="0" to-layer="187" to-port="1" />
+		<edge from-layer="187" from-port="2" to-layer="189" to-port="0" />
+		<edge from-layer="188" from-port="0" to-layer="189" to-port="1" />
+		<edge from-layer="189" from-port="2" to-layer="244" to-port="0" />
+		<edge from-layer="189" from-port="2" to-layer="263" to-port="1" />
+		<edge from-layer="189" from-port="2" to-layer="200" to-port="0" />
+		<edge from-layer="189" from-port="2" to-layer="217" to-port="0" />
+		<edge from-layer="189" from-port="2" to-layer="234" to-port="0" />
+		<edge from-layer="190" from-port="0" to-layer="191" to-port="0" />
+		<edge from-layer="191" from-port="1" to-layer="194" to-port="0" />
+		<edge from-layer="192" from-port="0" to-layer="193" to-port="0" />
+		<edge from-layer="193" from-port="1" to-layer="194" to-port="1" />
+		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
+		<edge from-layer="195" from-port="0" to-layer="196" to-port="1" />
+		<edge from-layer="196" from-port="2" to-layer="198" to-port="0" />
+		<edge from-layer="197" from-port="0" to-layer="198" to-port="1" />
+		<edge from-layer="198" from-port="2" to-layer="199" to-port="0" />
+		<edge from-layer="199" from-port="1" to-layer="200" to-port="1" />
+		<edge from-layer="200" from-port="2" to-layer="202" to-port="0" />
+		<edge from-layer="201" from-port="0" to-layer="202" to-port="1" />
+		<edge from-layer="202" from-port="2" to-layer="204" to-port="0" />
+		<edge from-layer="203" from-port="0" to-layer="204" 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="241" to-port="0" />
+		<edge from-layer="207" from-port="0" to-layer="208" to-port="0" />
+		<edge from-layer="208" from-port="1" to-layer="211" 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="211" to-port="1" />
+		<edge from-layer="211" from-port="2" to-layer="213" to-port="0" />
+		<edge from-layer="212" from-port="0" 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="216" to-port="0" />
+		<edge from-layer="216" from-port="1" to-layer="217" to-port="1" />
+		<edge from-layer="217" from-port="2" to-layer="219" to-port="0" />
+		<edge from-layer="218" from-port="0" to-layer="219" to-port="1" />
+		<edge from-layer="219" from-port="2" to-layer="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="223" to-port="0" />
+		<edge from-layer="222" from-port="0" to-layer="223" to-port="1" />
+		<edge from-layer="223" from-port="2" to-layer="241" to-port="1" />
+		<edge from-layer="224" from-port="0" to-layer="225" to-port="0" />
+		<edge from-layer="225" from-port="1" to-layer="228" to-port="0" />
+		<edge from-layer="226" from-port="0" to-layer="227" to-port="0" />
+		<edge from-layer="227" from-port="1" to-layer="228" to-port="1" />
+		<edge from-layer="228" from-port="2" to-layer="230" to-port="0" />
+		<edge from-layer="229" from-port="0" to-layer="230" to-port="1" />
+		<edge from-layer="230" from-port="2" to-layer="232" to-port="0" />
+		<edge from-layer="231" from-port="0" to-layer="232" to-port="1" />
+		<edge from-layer="232" from-port="2" 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="240" to-port="0" />
+		<edge from-layer="239" from-port="0" to-layer="240" to-port="1" />
+		<edge from-layer="240" from-port="2" to-layer="241" to-port="2" />
+		<edge from-layer="241" from-port="4" to-layer="243" to-port="0" />
+		<edge from-layer="242" from-port="0" to-layer="243" to-port="1" />
+		<edge from-layer="243" from-port="2" to-layer="249" to-port="0" />
+		<edge from-layer="244" from-port="1" to-layer="247" to-port="0" />
+		<edge from-layer="245" from-port="0" to-layer="247" to-port="1" />
+		<edge from-layer="246" from-port="0" to-layer="247" to-port="2" />
+		<edge from-layer="247" from-port="3" to-layer="248" to-port="0" />
+		<edge from-layer="248" from-port="2" 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="2" to-layer="265" to-port="0" />
+		<edge from-layer="264" from-port="0" to-layer="265" to-port="1" />
+		<edge from-layer="265" from-port="2" to-layer="267" to-port="0" />
+		<edge from-layer="266" from-port="0" to-layer="267" to-port="1" />
+		<edge from-layer="267" from-port="2" to-layer="269" to-port="0" />
+		<edge from-layer="268" from-port="0" to-layer="269" to-port="1" />
+		<edge from-layer="269" from-port="2" to-layer="280" to-port="0" />
+		<edge from-layer="269" from-port="2" to-layer="297" to-port="1" />
+		<edge from-layer="270" from-port="0" to-layer="271" to-port="0" />
+		<edge from-layer="271" from-port="1" to-layer="274" to-port="0" />
+		<edge from-layer="272" from-port="0" 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="278" to-port="0" />
+		<edge from-layer="277" from-port="0" to-layer="278" to-port="1" />
+		<edge from-layer="278" from-port="2" to-layer="279" to-port="0" />
+		<edge from-layer="279" from-port="1" to-layer="280" to-port="1" />
+		<edge from-layer="280" from-port="2" to-layer="282" to-port="0" />
+		<edge from-layer="281" from-port="0" to-layer="282" to-port="1" />
+		<edge from-layer="282" from-port="2" to-layer="283" to-port="0" />
+		<edge from-layer="283" from-port="1" to-layer="294" 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="297" to-port="0" />
+		<edge from-layer="297" from-port="2" to-layer="299" to-port="0" />
+		<edge from-layer="298" from-port="0" to-layer="299" to-port="1" />
+		<edge from-layer="299" from-port="2" to-layer="301" to-port="0" />
+		<edge from-layer="300" from-port="0" to-layer="301" to-port="1" />
+		<edge from-layer="301" from-port="2" to-layer="303" to-port="0" />
+		<edge from-layer="302" from-port="0" to-layer="303" to-port="1" />
+		<edge from-layer="303" from-port="2" to-layer="331" to-port="0" />
+		<edge from-layer="303" from-port="2" to-layer="358" to-port="0" />
+		<edge from-layer="303" from-port="2" to-layer="348" to-port="0" />
+		<edge from-layer="303" from-port="2" to-layer="314" to-port="0" />
+		<edge from-layer="303" from-port="2" to-layer="377" to-port="1" />
+		<edge from-layer="304" from-port="0" to-layer="305" to-port="0" />
+		<edge from-layer="305" from-port="1" to-layer="308" to-port="0" />
+		<edge from-layer="306" from-port="0" to-layer="307" to-port="0" />
+		<edge from-layer="307" from-port="1" to-layer="308" to-port="1" />
+		<edge from-layer="308" from-port="2" to-layer="310" to-port="0" />
+		<edge from-layer="309" from-port="0" to-layer="310" to-port="1" />
+		<edge from-layer="310" from-port="2" to-layer="312" to-port="0" />
+		<edge from-layer="311" from-port="0" to-layer="312" to-port="1" />
+		<edge from-layer="312" from-port="2" to-layer="313" to-port="0" />
+		<edge from-layer="313" from-port="1" to-layer="314" to-port="1" />
+		<edge from-layer="314" from-port="2" to-layer="316" to-port="0" />
+		<edge from-layer="315" from-port="0" to-layer="316" to-port="1" />
+		<edge from-layer="316" from-port="2" to-layer="318" to-port="0" />
+		<edge from-layer="317" from-port="0" to-layer="318" to-port="1" />
+		<edge from-layer="318" from-port="2" to-layer="320" to-port="0" />
+		<edge from-layer="319" from-port="0" to-layer="320" to-port="1" />
+		<edge from-layer="320" from-port="2" to-layer="355" 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="325" to-port="0" />
+		<edge from-layer="323" from-port="0" to-layer="324" to-port="0" />
+		<edge from-layer="324" from-port="1" 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="329" to-port="0" />
+		<edge from-layer="328" from-port="0" to-layer="329" to-port="1" />
+		<edge from-layer="329" from-port="2" to-layer="330" to-port="0" />
+		<edge from-layer="330" from-port="1" 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="337" to-port="0" />
+		<edge from-layer="336" from-port="0" to-layer="337" to-port="1" />
+		<edge from-layer="337" from-port="2" to-layer="355" to-port="1" />
+		<edge from-layer="338" from-port="0" to-layer="339" to-port="0" />
+		<edge from-layer="339" from-port="1" to-layer="342" to-port="0" />
+		<edge from-layer="340" from-port="0" to-layer="341" to-port="0" />
+		<edge from-layer="341" from-port="1" to-layer="342" to-port="1" />
+		<edge from-layer="342" from-port="2" to-layer="344" to-port="0" />
+		<edge from-layer="343" from-port="0" to-layer="344" to-port="1" />
+		<edge from-layer="344" from-port="2" to-layer="346" to-port="0" />
+		<edge from-layer="345" from-port="0" to-layer="346" to-port="1" />
+		<edge from-layer="346" from-port="2" to-layer="347" to-port="0" />
+		<edge from-layer="347" from-port="1" to-layer="348" to-port="1" />
+		<edge from-layer="348" from-port="2" to-layer="350" to-port="0" />
+		<edge from-layer="349" from-port="0" to-layer="350" to-port="1" />
+		<edge from-layer="350" from-port="2" to-layer="352" to-port="0" />
+		<edge from-layer="351" from-port="0" to-layer="352" to-port="1" />
+		<edge from-layer="352" from-port="2" to-layer="354" to-port="0" />
+		<edge from-layer="353" from-port="0" to-layer="354" to-port="1" />
+		<edge from-layer="354" from-port="2" to-layer="355" to-port="2" />
+		<edge from-layer="355" from-port="4" to-layer="357" to-port="0" />
+		<edge from-layer="356" from-port="0" to-layer="357" to-port="1" />
+		<edge from-layer="357" from-port="2" to-layer="363" to-port="0" />
+		<edge from-layer="358" from-port="1" to-layer="361" to-port="0" />
+		<edge from-layer="359" from-port="0" to-layer="361" to-port="1" />
+		<edge from-layer="360" from-port="0" to-layer="361" to-port="2" />
+		<edge from-layer="361" from-port="3" to-layer="362" to-port="0" />
+		<edge from-layer="362" from-port="2" to-layer="363" to-port="1" />
+		<edge from-layer="363" from-port="2" to-layer="374" to-port="0" />
+		<edge from-layer="364" from-port="0" to-layer="365" to-port="0" />
+		<edge from-layer="365" from-port="1" to-layer="368" to-port="0" />
+		<edge from-layer="366" from-port="0" to-layer="367" to-port="0" />
+		<edge from-layer="367" from-port="1" to-layer="368" to-port="1" />
+		<edge from-layer="368" from-port="2" to-layer="370" to-port="0" />
+		<edge from-layer="369" from-port="0" to-layer="370" to-port="1" />
+		<edge from-layer="370" from-port="2" to-layer="372" to-port="0" />
+		<edge from-layer="371" from-port="0" to-layer="372" to-port="1" />
+		<edge from-layer="372" from-port="2" to-layer="373" to-port="0" />
+		<edge from-layer="373" from-port="1" to-layer="374" to-port="1" />
+		<edge from-layer="374" from-port="2" to-layer="376" to-port="0" />
+		<edge from-layer="375" from-port="0" to-layer="376" to-port="1" />
+		<edge from-layer="376" from-port="2" to-layer="377" to-port="0" />
+		<edge from-layer="377" from-port="2" to-layer="379" to-port="0" />
+		<edge from-layer="378" from-port="0" to-layer="379" to-port="1" />
+		<edge from-layer="379" from-port="2" to-layer="381" to-port="0" />
+		<edge from-layer="380" from-port="0" to-layer="381" to-port="1" />
+		<edge from-layer="381" from-port="2" to-layer="383" to-port="0" />
+		<edge from-layer="382" from-port="0" to-layer="383" to-port="1" />
+		<edge from-layer="383" from-port="2" to-layer="394" to-port="0" />
+		<edge from-layer="383" from-port="2" to-layer="411" to-port="1" />
+		<edge from-layer="384" from-port="0" to-layer="385" to-port="0" />
+		<edge from-layer="385" from-port="1" to-layer="388" to-port="0" />
+		<edge from-layer="386" from-port="0" 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="390" to-port="0" />
+		<edge from-layer="389" from-port="0" to-layer="390" to-port="1" />
+		<edge from-layer="390" from-port="2" to-layer="392" to-port="0" />
+		<edge from-layer="391" from-port="0" 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="394" to-port="1" />
+		<edge from-layer="394" from-port="2" to-layer="396" to-port="0" />
+		<edge from-layer="395" from-port="0" to-layer="396" to-port="1" />
+		<edge from-layer="396" from-port="2" to-layer="397" to-port="0" />
+		<edge from-layer="397" from-port="1" to-layer="408" to-port="0" />
+		<edge from-layer="398" from-port="0" to-layer="399" to-port="0" />
+		<edge from-layer="399" from-port="1" to-layer="402" to-port="0" />
+		<edge from-layer="400" from-port="0" to-layer="401" to-port="0" />
+		<edge from-layer="401" from-port="1" to-layer="402" to-port="1" />
+		<edge from-layer="402" from-port="2" to-layer="404" to-port="0" />
+		<edge from-layer="403" from-port="0" 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="1" to-layer="408" to-port="1" />
+		<edge from-layer="408" from-port="2" to-layer="410" to-port="0" />
+		<edge from-layer="409" from-port="0" to-layer="410" to-port="1" />
+		<edge from-layer="410" from-port="2" to-layer="411" to-port="0" />
+		<edge from-layer="411" from-port="2" to-layer="413" to-port="0" />
+		<edge from-layer="412" from-port="0" to-layer="413" to-port="1" />
+		<edge from-layer="413" from-port="2" to-layer="415" to-port="0" />
+		<edge from-layer="414" from-port="0" to-layer="415" to-port="1" />
+		<edge from-layer="415" from-port="2" to-layer="417" to-port="0" />
+		<edge from-layer="416" from-port="0" to-layer="417" to-port="1" />
+		<edge from-layer="417" from-port="2" to-layer="428" to-port="0" />
+		<edge from-layer="417" from-port="2" to-layer="445" to-port="0" />
+		<edge from-layer="417" from-port="2" to-layer="462" to-port="0" />
+		<edge from-layer="417" from-port="2" to-layer="472" to-port="0" />
+		<edge from-layer="417" from-port="2" to-layer="491" to-port="1" />
+		<edge from-layer="418" from-port="0" to-layer="419" to-port="0" />
+		<edge from-layer="419" from-port="1" to-layer="422" to-port="0" />
+		<edge from-layer="420" from-port="0" to-layer="421" to-port="0" />
+		<edge from-layer="421" from-port="1" to-layer="422" to-port="1" />
+		<edge from-layer="422" from-port="2" to-layer="424" to-port="0" />
+		<edge from-layer="423" from-port="0" to-layer="424" to-port="1" />
+		<edge from-layer="424" from-port="2" to-layer="426" to-port="0" />
+		<edge from-layer="425" from-port="0" to-layer="426" to-port="1" />
+		<edge from-layer="426" from-port="2" to-layer="427" to-port="0" />
+		<edge from-layer="427" from-port="1" to-layer="428" to-port="1" />
+		<edge from-layer="428" from-port="2" to-layer="430" 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="469" 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="449" to-port="0" />
+		<edge from-layer="448" from-port="0" to-layer="449" to-port="1" />
+		<edge from-layer="449" from-port="2" to-layer="451" to-port="0" />
+		<edge from-layer="450" from-port="0" to-layer="451" to-port="1" />
+		<edge from-layer="451" from-port="2" to-layer="469" to-port="1" />
+		<edge from-layer="452" from-port="0" to-layer="453" to-port="0" />
+		<edge from-layer="453" from-port="1" to-layer="456" to-port="0" />
+		<edge from-layer="454" from-port="0" to-layer="455" to-port="0" />
+		<edge from-layer="455" from-port="1" to-layer="456" to-port="1" />
+		<edge from-layer="456" from-port="2" to-layer="458" to-port="0" />
+		<edge from-layer="457" from-port="0" to-layer="458" to-port="1" />
+		<edge from-layer="458" from-port="2" to-layer="460" to-port="0" />
+		<edge from-layer="459" from-port="0" to-layer="460" to-port="1" />
+		<edge from-layer="460" from-port="2" to-layer="461" to-port="0" />
+		<edge from-layer="461" from-port="1" to-layer="462" to-port="1" />
+		<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="469" to-port="2" />
+		<edge from-layer="469" from-port="4" to-layer="471" to-port="0" />
+		<edge from-layer="470" from-port="0" to-layer="471" to-port="1" />
+		<edge from-layer="471" from-port="2" to-layer="477" to-port="0" />
+		<edge from-layer="472" from-port="1" to-layer="475" to-port="0" />
+		<edge from-layer="473" from-port="0" to-layer="475" to-port="1" />
+		<edge from-layer="474" from-port="0" to-layer="475" to-port="2" />
+		<edge from-layer="475" from-port="3" to-layer="476" to-port="0" />
+		<edge from-layer="476" from-port="2" to-layer="477" to-port="1" />
+		<edge from-layer="477" from-port="2" to-layer="488" to-port="0" />
+		<edge from-layer="478" from-port="0" to-layer="479" to-port="0" />
+		<edge from-layer="479" from-port="1" to-layer="482" to-port="0" />
+		<edge from-layer="480" from-port="0" to-layer="481" to-port="0" />
+		<edge from-layer="481" from-port="1" to-layer="482" to-port="1" />
+		<edge from-layer="482" from-port="2" to-layer="484" to-port="0" />
+		<edge from-layer="483" from-port="0" to-layer="484" to-port="1" />
+		<edge from-layer="484" from-port="2" to-layer="486" to-port="0" />
+		<edge from-layer="485" from-port="0" to-layer="486" to-port="1" />
+		<edge from-layer="486" from-port="2" to-layer="487" to-port="0" />
+		<edge from-layer="487" from-port="1" to-layer="488" to-port="1" />
+		<edge from-layer="488" from-port="2" to-layer="490" to-port="0" />
+		<edge from-layer="489" from-port="0" to-layer="490" to-port="1" />
+		<edge from-layer="490" from-port="2" to-layer="491" to-port="0" />
+		<edge from-layer="491" from-port="2" to-layer="493" to-port="0" />
+		<edge from-layer="492" from-port="0" to-layer="493" to-port="1" />
+		<edge from-layer="493" from-port="2" to-layer="495" to-port="0" />
+		<edge from-layer="494" from-port="0" to-layer="495" to-port="1" />
+		<edge from-layer="495" from-port="2" to-layer="497" to-port="0" />
+		<edge from-layer="496" from-port="0" to-layer="497" to-port="1" />
+		<edge from-layer="497" from-port="2" to-layer="508" to-port="0" />
+		<edge from-layer="497" from-port="2" to-layer="525" to-port="1" />
+		<edge from-layer="498" from-port="0" to-layer="499" to-port="0" />
+		<edge from-layer="499" from-port="1" to-layer="502" to-port="0" />
+		<edge from-layer="500" from-port="0" to-layer="501" to-port="0" />
+		<edge from-layer="501" from-port="1" to-layer="502" to-port="1" />
+		<edge from-layer="502" from-port="2" to-layer="504" to-port="0" />
+		<edge from-layer="503" from-port="0" to-layer="504" to-port="1" />
+		<edge from-layer="504" from-port="2" to-layer="506" to-port="0" />
+		<edge from-layer="505" from-port="0" to-layer="506" to-port="1" />
+		<edge from-layer="506" from-port="2" 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="511" to-port="0" />
+		<edge from-layer="511" from-port="1" to-layer="522" to-port="0" />
+		<edge from-layer="512" from-port="0" to-layer="513" to-port="0" />
+		<edge from-layer="513" from-port="1" to-layer="516" to-port="0" />
+		<edge from-layer="514" from-port="0" to-layer="515" to-port="0" />
+		<edge from-layer="515" from-port="1" 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="0" />
+		<edge from-layer="521" from-port="1" to-layer="522" to-port="1" />
+		<edge from-layer="522" from-port="2" to-layer="524" to-port="0" />
+		<edge from-layer="523" from-port="0" to-layer="524" to-port="1" />
+		<edge from-layer="524" from-port="2" to-layer="525" to-port="0" />
+		<edge from-layer="525" from-port="2" to-layer="527" to-port="0" />
+		<edge from-layer="526" from-port="0" to-layer="527" to-port="1" />
+		<edge from-layer="527" from-port="2" to-layer="529" to-port="0" />
+		<edge from-layer="528" from-port="0" to-layer="529" to-port="1" />
+		<edge from-layer="529" from-port="2" to-layer="531" to-port="0" />
+		<edge from-layer="530" from-port="0" to-layer="531" to-port="1" />
+		<edge from-layer="531" from-port="2" to-layer="559" to-port="0" />
+		<edge from-layer="531" from-port="2" to-layer="576" to-port="0" />
+		<edge from-layer="531" from-port="2" to-layer="586" to-port="0" />
+		<edge from-layer="531" from-port="2" to-layer="605" to-port="1" />
+		<edge from-layer="531" from-port="2" to-layer="542" to-port="0" />
+		<edge from-layer="532" from-port="0" to-layer="533" to-port="0" />
+		<edge from-layer="533" from-port="1" to-layer="536" to-port="0" />
+		<edge from-layer="534" from-port="0" 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="540" to-port="0" />
+		<edge from-layer="539" from-port="0" to-layer="540" to-port="1" />
+		<edge from-layer="540" from-port="2" to-layer="541" to-port="0" />
+		<edge from-layer="541" from-port="1" to-layer="542" to-port="1" />
+		<edge from-layer="542" from-port="2" to-layer="544" to-port="0" />
+		<edge from-layer="543" from-port="0" to-layer="544" to-port="1" />
+		<edge from-layer="544" from-port="2" to-layer="546" to-port="0" />
+		<edge from-layer="545" from-port="0" to-layer="546" to-port="1" />
+		<edge from-layer="546" from-port="2" to-layer="548" to-port="0" />
+		<edge from-layer="547" from-port="0" to-layer="548" to-port="1" />
+		<edge from-layer="548" from-port="2" to-layer="583" to-port="0" />
+		<edge from-layer="549" from-port="0" to-layer="550" to-port="0" />
+		<edge from-layer="550" from-port="1" to-layer="553" to-port="0" />
+		<edge from-layer="551" from-port="0" to-layer="552" to-port="0" />
+		<edge from-layer="552" from-port="1" to-layer="553" to-port="1" />
+		<edge from-layer="553" from-port="2" to-layer="555" to-port="0" />
+		<edge from-layer="554" from-port="0" to-layer="555" to-port="1" />
+		<edge from-layer="555" from-port="2" to-layer="557" to-port="0" />
+		<edge from-layer="556" from-port="0" to-layer="557" to-port="1" />
+		<edge from-layer="557" from-port="2" to-layer="558" to-port="0" />
+		<edge from-layer="558" from-port="1" to-layer="559" to-port="1" />
+		<edge from-layer="559" from-port="2" to-layer="561" to-port="0" />
+		<edge from-layer="560" from-port="0" to-layer="561" to-port="1" />
+		<edge from-layer="561" from-port="2" to-layer="563" to-port="0" />
+		<edge from-layer="562" from-port="0" to-layer="563" to-port="1" />
+		<edge from-layer="563" from-port="2" to-layer="565" to-port="0" />
+		<edge from-layer="564" from-port="0" to-layer="565" to-port="1" />
+		<edge from-layer="565" from-port="2" to-layer="583" to-port="1" />
+		<edge from-layer="566" from-port="0" to-layer="567" to-port="0" />
+		<edge from-layer="567" from-port="1" to-layer="570" to-port="0" />
+		<edge from-layer="568" from-port="0" to-layer="569" to-port="0" />
+		<edge from-layer="569" from-port="1" to-layer="570" to-port="1" />
+		<edge from-layer="570" from-port="2" to-layer="572" to-port="0" />
+		<edge from-layer="571" from-port="0" to-layer="572" to-port="1" />
+		<edge from-layer="572" from-port="2" to-layer="574" to-port="0" />
+		<edge from-layer="573" from-port="0" to-layer="574" to-port="1" />
+		<edge from-layer="574" from-port="2" to-layer="575" to-port="0" />
+		<edge from-layer="575" from-port="1" to-layer="576" to-port="1" />
+		<edge from-layer="576" from-port="2" to-layer="578" to-port="0" />
+		<edge from-layer="577" from-port="0" to-layer="578" to-port="1" />
+		<edge from-layer="578" from-port="2" to-layer="580" to-port="0" />
+		<edge from-layer="579" from-port="0" to-layer="580" to-port="1" />
+		<edge from-layer="580" from-port="2" to-layer="582" to-port="0" />
+		<edge from-layer="581" from-port="0" to-layer="582" to-port="1" />
+		<edge from-layer="582" from-port="2" to-layer="583" to-port="2" />
+		<edge from-layer="583" from-port="4" 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="591" to-port="0" />
+		<edge from-layer="586" from-port="1" to-layer="589" to-port="0" />
+		<edge from-layer="587" from-port="0" to-layer="589" to-port="1" />
+		<edge from-layer="588" from-port="0" to-layer="589" to-port="2" />
+		<edge from-layer="589" from-port="3" to-layer="590" to-port="0" />
+		<edge from-layer="590" from-port="2" to-layer="591" to-port="1" />
+		<edge from-layer="591" from-port="2" to-layer="602" to-port="0" />
+		<edge from-layer="592" from-port="0" to-layer="593" to-port="0" />
+		<edge from-layer="593" from-port="1" to-layer="596" to-port="0" />
+		<edge from-layer="594" from-port="0" to-layer="595" to-port="0" />
+		<edge from-layer="595" from-port="1" to-layer="596" to-port="1" />
+		<edge from-layer="596" from-port="2" to-layer="598" to-port="0" />
+		<edge from-layer="597" from-port="0" to-layer="598" to-port="1" />
+		<edge from-layer="598" from-port="2" to-layer="600" to-port="0" />
+		<edge from-layer="599" from-port="0" to-layer="600" to-port="1" />
+		<edge from-layer="600" from-port="2" to-layer="601" to-port="0" />
+		<edge from-layer="601" from-port="1" to-layer="602" to-port="1" />
+		<edge from-layer="602" from-port="2" to-layer="604" to-port="0" />
+		<edge from-layer="603" from-port="0" to-layer="604" to-port="1" />
+		<edge from-layer="604" from-port="2" to-layer="605" to-port="0" />
+		<edge from-layer="605" from-port="2" to-layer="607" to-port="0" />
+		<edge from-layer="606" from-port="0" to-layer="607" to-port="1" />
+		<edge from-layer="607" from-port="2" to-layer="609" to-port="0" />
+		<edge from-layer="608" from-port="0" to-layer="609" to-port="1" />
+		<edge from-layer="609" from-port="2" to-layer="611" to-port="0" />
+		<edge from-layer="610" from-port="0" to-layer="611" to-port="1" />
+		<edge from-layer="611" from-port="2" to-layer="622" to-port="0" />
+		<edge from-layer="611" from-port="2" to-layer="639" to-port="1" />
+		<edge from-layer="612" from-port="0" to-layer="613" to-port="0" />
+		<edge from-layer="613" from-port="1" to-layer="616" to-port="0" />
+		<edge from-layer="614" from-port="0" to-layer="615" to-port="0" />
+		<edge from-layer="615" from-port="1" to-layer="616" to-port="1" />
+		<edge from-layer="616" from-port="2" to-layer="618" to-port="0" />
+		<edge from-layer="617" from-port="0" to-layer="618" to-port="1" />
+		<edge from-layer="618" from-port="2" to-layer="620" to-port="0" />
+		<edge from-layer="619" from-port="0" to-layer="620" to-port="1" />
+		<edge from-layer="620" from-port="2" to-layer="621" to-port="0" />
+		<edge from-layer="621" from-port="1" to-layer="622" to-port="1" />
+		<edge from-layer="622" from-port="2" to-layer="624" to-port="0" />
+		<edge from-layer="623" from-port="0" to-layer="624" to-port="1" />
+		<edge from-layer="624" from-port="2" to-layer="625" to-port="0" />
+		<edge from-layer="625" from-port="1" to-layer="636" to-port="0" />
+		<edge from-layer="626" from-port="0" to-layer="627" to-port="0" />
+		<edge from-layer="627" from-port="1" to-layer="630" to-port="0" />
+		<edge from-layer="628" from-port="0" 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="634" to-port="0" />
+		<edge from-layer="633" from-port="0" to-layer="634" to-port="1" />
+		<edge from-layer="634" from-port="2" to-layer="635" to-port="0" />
+		<edge from-layer="635" from-port="1" to-layer="636" to-port="1" />
+		<edge from-layer="636" from-port="2" to-layer="638" to-port="0" />
+		<edge from-layer="637" from-port="0" to-layer="638" to-port="1" />
+		<edge from-layer="638" from-port="2" to-layer="639" to-port="0" />
+		<edge from-layer="639" from-port="2" to-layer="641" to-port="0" />
+		<edge from-layer="640" from-port="0" to-layer="641" to-port="1" />
+		<edge from-layer="641" from-port="2" to-layer="643" to-port="0" />
+		<edge from-layer="642" from-port="0" to-layer="643" to-port="1" />
+		<edge from-layer="643" from-port="2" to-layer="645" to-port="0" />
+		<edge from-layer="644" from-port="0" to-layer="645" to-port="1" />
+		<edge from-layer="645" from-port="2" to-layer="719" to-port="1" />
+		<edge from-layer="645" from-port="2" to-layer="656" to-port="0" />
+		<edge from-layer="645" from-port="2" to-layer="673" to-port="0" />
+		<edge from-layer="645" from-port="2" to-layer="690" to-port="0" />
+		<edge from-layer="645" from-port="2" to-layer="700" to-port="0" />
+		<edge from-layer="646" from-port="0" to-layer="647" to-port="0" />
+		<edge from-layer="647" from-port="1" to-layer="650" to-port="0" />
+		<edge from-layer="648" from-port="0" to-layer="649" to-port="0" />
+		<edge from-layer="649" from-port="1" to-layer="650" to-port="1" />
+		<edge from-layer="650" from-port="2" to-layer="652" to-port="0" />
+		<edge from-layer="651" from-port="0" to-layer="652" to-port="1" />
+		<edge from-layer="652" from-port="2" to-layer="654" to-port="0" />
+		<edge from-layer="653" from-port="0" to-layer="654" to-port="1" />
+		<edge from-layer="654" from-port="2" to-layer="655" to-port="0" />
+		<edge from-layer="655" from-port="1" to-layer="656" to-port="1" />
+		<edge from-layer="656" from-port="2" to-layer="658" to-port="0" />
+		<edge from-layer="657" from-port="0" 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="697" to-port="0" />
+		<edge from-layer="663" from-port="0" to-layer="664" to-port="0" />
+		<edge from-layer="664" from-port="1" to-layer="667" to-port="0" />
+		<edge from-layer="665" from-port="0" to-layer="666" to-port="0" />
+		<edge from-layer="666" from-port="1" to-layer="667" to-port="1" />
+		<edge from-layer="667" from-port="2" to-layer="669" to-port="0" />
+		<edge from-layer="668" from-port="0" to-layer="669" to-port="1" />
+		<edge from-layer="669" from-port="2" to-layer="671" to-port="0" />
+		<edge from-layer="670" from-port="0" to-layer="671" to-port="1" />
+		<edge from-layer="671" from-port="2" to-layer="672" to-port="0" />
+		<edge from-layer="672" from-port="1" to-layer="673" to-port="1" />
+		<edge from-layer="673" from-port="2" to-layer="675" to-port="0" />
+		<edge from-layer="674" from-port="0" 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="697" to-port="1" />
+		<edge from-layer="680" from-port="0" to-layer="681" to-port="0" />
+		<edge from-layer="681" from-port="1" to-layer="684" to-port="0" />
+		<edge from-layer="682" from-port="0" to-layer="683" to-port="0" />
+		<edge from-layer="683" from-port="1" to-layer="684" to-port="1" />
+		<edge from-layer="684" from-port="2" to-layer="686" to-port="0" />
+		<edge from-layer="685" from-port="0" to-layer="686" to-port="1" />
+		<edge from-layer="686" from-port="2" to-layer="688" to-port="0" />
+		<edge from-layer="687" from-port="0" to-layer="688" to-port="1" />
+		<edge from-layer="688" from-port="2" to-layer="689" to-port="0" />
+		<edge from-layer="689" from-port="1" to-layer="690" to-port="1" />
+		<edge from-layer="690" from-port="2" to-layer="692" to-port="0" />
+		<edge from-layer="691" from-port="0" to-layer="692" to-port="1" />
+		<edge from-layer="692" from-port="2" to-layer="694" to-port="0" />
+		<edge from-layer="693" from-port="0" to-layer="694" to-port="1" />
+		<edge from-layer="694" from-port="2" to-layer="696" to-port="0" />
+		<edge from-layer="695" from-port="0" to-layer="696" to-port="1" />
+		<edge from-layer="696" from-port="2" to-layer="697" to-port="2" />
+		<edge from-layer="697" from-port="4" to-layer="699" to-port="0" />
+		<edge from-layer="698" from-port="0" to-layer="699" to-port="1" />
+		<edge from-layer="699" from-port="2" to-layer="705" to-port="0" />
+		<edge from-layer="700" from-port="1" to-layer="703" to-port="0" />
+		<edge from-layer="701" from-port="0" to-layer="703" to-port="1" />
+		<edge from-layer="702" from-port="0" to-layer="703" to-port="2" />
+		<edge from-layer="703" from-port="3" to-layer="704" to-port="0" />
+		<edge from-layer="704" from-port="2" to-layer="705" to-port="1" />
+		<edge from-layer="705" from-port="2" to-layer="716" to-port="0" />
+		<edge from-layer="706" from-port="0" to-layer="707" to-port="0" />
+		<edge from-layer="707" from-port="1" to-layer="710" to-port="0" />
+		<edge from-layer="708" from-port="0" to-layer="709" to-port="0" />
+		<edge from-layer="709" from-port="1" to-layer="710" to-port="1" />
+		<edge from-layer="710" from-port="2" to-layer="712" to-port="0" />
+		<edge from-layer="711" from-port="0" to-layer="712" to-port="1" />
+		<edge from-layer="712" from-port="2" to-layer="714" to-port="0" />
+		<edge from-layer="713" from-port="0" to-layer="714" to-port="1" />
+		<edge from-layer="714" from-port="2" to-layer="715" to-port="0" />
+		<edge from-layer="715" from-port="1" to-layer="716" to-port="1" />
+		<edge from-layer="716" from-port="2" to-layer="718" to-port="0" />
+		<edge from-layer="717" from-port="0" to-layer="718" to-port="1" />
+		<edge from-layer="718" from-port="2" to-layer="719" to-port="0" />
+		<edge from-layer="719" from-port="2" to-layer="721" to-port="0" />
+		<edge from-layer="720" from-port="0" 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="725" to-port="0" />
+		<edge from-layer="724" from-port="0" to-layer="725" to-port="1" />
+		<edge from-layer="725" from-port="2" to-layer="736" to-port="0" />
+		<edge from-layer="725" from-port="2" to-layer="751" to-port="1" />
+		<edge from-layer="726" from-port="0" to-layer="727" to-port="0" />
+		<edge from-layer="727" from-port="1" to-layer="730" to-port="0" />
+		<edge from-layer="728" from-port="0" to-layer="729" to-port="0" />
+		<edge from-layer="729" from-port="1" to-layer="730" to-port="1" />
+		<edge from-layer="730" from-port="2" to-layer="732" to-port="0" />
+		<edge from-layer="731" from-port="0" to-layer="732" to-port="1" />
+		<edge from-layer="732" from-port="2" to-layer="734" to-port="0" />
+		<edge from-layer="733" from-port="0" to-layer="734" to-port="1" />
+		<edge from-layer="734" from-port="2" to-layer="735" to-port="0" />
+		<edge from-layer="735" from-port="1" to-layer="736" to-port="1" />
+		<edge from-layer="736" from-port="2" to-layer="738" to-port="0" />
+		<edge from-layer="737" from-port="0" to-layer="738" to-port="1" />
+		<edge from-layer="738" from-port="2" to-layer="739" to-port="0" />
+		<edge from-layer="739" from-port="1" to-layer="748" to-port="0" />
+		<edge from-layer="740" from-port="0" to-layer="741" to-port="0" />
+		<edge from-layer="741" from-port="1" to-layer="744" to-port="0" />
+		<edge from-layer="742" from-port="0" to-layer="743" to-port="0" />
+		<edge from-layer="743" from-port="1" to-layer="744" to-port="1" />
+		<edge from-layer="744" from-port="2" to-layer="746" to-port="0" />
+		<edge from-layer="745" from-port="0" to-layer="746" to-port="1" />
+		<edge from-layer="746" from-port="2" to-layer="747" to-port="0" />
+		<edge from-layer="747" from-port="1" to-layer="748" to-port="1" />
+		<edge from-layer="748" from-port="2" to-layer="750" to-port="0" />
+		<edge from-layer="749" from-port="0" to-layer="750" to-port="1" />
+		<edge from-layer="750" from-port="2" to-layer="751" to-port="0" />
+		<edge from-layer="751" from-port="2" to-layer="753" to-port="0" />
+		<edge from-layer="752" from-port="0" to-layer="753" to-port="1" />
+		<edge from-layer="753" from-port="2" to-layer="755" to-port="0" />
+		<edge from-layer="754" from-port="0" to-layer="755" to-port="1" />
+		<edge from-layer="755" from-port="2" to-layer="757" to-port="0" />
+		<edge from-layer="756" from-port="0" to-layer="757" to-port="1" />
+		<edge from-layer="757" from-port="2" to-layer="758" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2024.3.0-16041-1e3b88e4e3f-releases/2024/3" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<weight_compression>
+				<all_layers value="False" />
+				<awq value="False" />
+				<gptq value="False" />
+				<group_size value="128" />
+				<ignored_scope value="[]" />
+				<mode value="int4_asym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.12.0" />
+			<optimum_intel_version value="1.18.2" />
+			<optimum_version value="1.21.3" />
+			<pytorch_version value="2.4.0" />
+			<transformers_version value="4.43.4" />
+		</optimum>
+	</rt_info>
+</net>