diff --git "a/openvino_encoder_model.xml" "b/openvino_encoder_model.xml"
new file mode 100644--- /dev/null
+++ "b/openvino_encoder_model.xml"
@@ -0,0 +1,7009 @@
+<?xml version="1.0"?>
+<net name="Model0" version="11">
+	<layers>
+		<layer id="0" name="input_features" type="Parameter" version="opset1">
+			<data shape="?,80,3000" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="input_features">
+					<dim>-1</dim>
+					<dim>80</dim>
+					<dim>3000</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 80, 3" offset="0" size="92160" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_17189" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1, 1" offset="92160" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Convert_17192" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="self.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="self.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1, 1" offset="92544" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="self.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="self.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>80</dim>
+					<dim>3000</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>80</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>3000</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="__module.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 384, 1" offset="93312" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="__module.conv1/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>3000</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="47">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>3000</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>3000</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="17">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>3000</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="self.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384, 3" offset="94848" size="442368" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="Convert_17002" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="self.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1, 1" offset="537216" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Convert_17005" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="self.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="self.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1, 1" offset="537600" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="self.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="self.conv2.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>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="__module.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="2" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>3000</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="__module.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 384, 1" offset="538368" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="__module.conv2/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>1500</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="59">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="aten::gelu/Gelu_1" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>1500</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="20,inputs_embeds.1">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_116" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="539904" size="24" />
+			<output>
+				<port id="0" precision="I64" names="24">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="aten::permute/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>384</dim>
+					<dim>1500</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="25,inputs_embeds">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_4296" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1500, 384" offset="539928" size="2304000" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="27,input.1">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="Constant_4297" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="2843932" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="Constant_4298" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="2845468" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="84,hidden_states.1">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="Constant_4241" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="2847004" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="Convert_17035" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="Constant_4241/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="2994460" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Convert_17038" 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="39" name="Constant_4241/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="40" name="Constant_4241/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="2994844" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="41" name="Constant_4241/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="42" name="Constant_4241/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="43" name="Multiply_4224" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="44" name="Constant_4299" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="2995612" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="__module.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="94,tensor.1">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="Constant_4375" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="__module.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="96">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="48" name="__module.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="49" name="__module.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="97">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="50" name="self.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="2997196" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="51" name="Convert_17024" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="52" name="self.layers.0.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="3144652" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="53" name="Convert_17027" 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="54" name="self.layers.0.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="55" name="self.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="3145036" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="56" name="self.layers.0.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="57" name="self.layers.0.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="58" name="__module.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="100,tensor.3">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="59" name="Constant_4376" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="60" name="__module.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="102">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="61" name="__module.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="62" name="__module.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="103">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="63" name="__module.layers.0.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="113,input.3">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="64" name="__module.layers.0.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="114,input.5">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="65" name="self.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="3145804" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="66" name="Convert_17013" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="67" name="self.layers.0.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="3293260" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="68" name="Convert_17016" 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="69" name="self.layers.0.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="70" name="self.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="3293644" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="71" name="self.layers.0.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="72" name="self.layers.0.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="73" name="__module.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="74" name="Constant_4300" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="3294412" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="75" name="__module.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="107,tensor.5">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="76" name="Constant_4377" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="77" name="__module.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="109">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="78" name="__module.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="79" name="__module.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="110">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="80" name="__module.layers.0.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="116,attn_output.1">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="81" name="__module.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="82" name="__module.layers.0.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="117,attn_output.3">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="83" name="Constant_4378" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="3295948" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="84" name="__module.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="119">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="85" name="self.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="3295972" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="86" name="Convert_17046" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="87" name="self.layers.0.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="3443428" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="88" name="Convert_17049" 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="89" name="self.layers.0.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="90" name="self.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="3443812" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="91" name="self.layers.0.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="92" name="self.layers.0.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="93" name="__module.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="94" name="Constant_4301" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="3444580" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="95" name="__module.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="122,input.7">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="96" name="__module.layers.0/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="124,residual.3">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="97" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="98" name="__module.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="99" name="Constant_4302" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="3446116" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="100" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="101" name="Constant_4303" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="3447652" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="102" name="__module.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="128">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="103" name="self.layers.0.fc1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 384" offset="3449188" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="104" name="Convert_16914" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="105" name="self.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 1" offset="4039012" size="1536" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="106" name="Convert_16917" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="107" name="self.layers.0.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="108" name="self.layers.0.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 1" offset="4040548" size="3072" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="109" name="self.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="110" name="self.layers.0.fc1.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="111" name="__module.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="112" name="Constant_4304" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="4043620" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="113" name="__module.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="131">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="114" name="__module.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="132,input.9">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="115" name="self.layers.0.fc2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1536" offset="4049764" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="116" name="Convert_16925" 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="117" name="self.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="4639588" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="118" name="Convert_16928" 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="119" name="self.layers.0.fc2.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="120" name="self.layers.0.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="4639972" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="121" name="self.layers.0.fc2.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="122" name="self.layers.0.fc2.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="123" name="__module.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="124" name="Constant_4305" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="4640740" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="125" name="__module.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="136,input.11">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="126" name="__module.layers.0/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="138,residual.5">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="127" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="128" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="129" name="Constant_4306" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="4642276" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="130" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="131" name="Constant_4307" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="4643812" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="132" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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,hidden_states.7">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="133" name="Constant_4244" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="4645348" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="134" name="Convert_17079" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="135" name="Constant_4244/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="4792804" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="136" name="Convert_17082" 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="137" name="Constant_4244/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="138" name="Constant_4244/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="4793188" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="139" name="Constant_4244/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="140" name="Constant_4244/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="141" name="Multiply_4228" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="142" name="Constant_4308" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="4793956" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="143" name="__module.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="173,tensor.7">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="144" name="Constant_4379" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="145" name="__module.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="175">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="146" name="__module.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="147" name="__module.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="176">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="148" name="self.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="4795492" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="149" name="Convert_17068" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="150" name="self.layers.1.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="4942948" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="151" name="Convert_17071" 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="152" name="self.layers.1.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="153" name="self.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="4943332" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="154" name="self.layers.1.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="155" name="self.layers.1.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="156" name="__module.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="179,tensor.9">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="157" name="Constant_4380" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="158" name="__module.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="181">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="159" name="__module.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="160" name="__module.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="182">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="161" name="__module.layers.1.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="192,input.13">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="162" name="__module.layers.1.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="193,input.15">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="163" name="self.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="4944100" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="164" name="Convert_17057" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="165" name="self.layers.1.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="5091556" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="166" name="Convert_17060" 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="167" name="self.layers.1.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="168" name="self.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="5091940" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="169" name="self.layers.1.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="170" name="self.layers.1.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="171" name="__module.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="172" name="Constant_4309" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="5092708" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="173" name="__module.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="186,tensor.11">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="174" name="Constant_4381" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="175" name="__module.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="188">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="176" name="__module.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="177" name="__module.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="189">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="178" name="__module.layers.1.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="195,attn_output.5">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="179" name="__module.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="180" name="__module.layers.1.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="196,attn_output.7">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="181" name="Constant_4382" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="3295948" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="182" name="__module.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="198">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="183" name="self.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="5094244" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="184" name="Convert_17090" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="185" name="self.layers.1.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="5241700" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="186" name="Convert_17093" 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="187" name="self.layers.1.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="188" name="self.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="5242084" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="189" name="self.layers.1.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="190" name="self.layers.1.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="191" name="__module.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="192" name="Constant_4310" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="5242852" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="193" name="__module.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="201,input.17">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="194" name="__module.layers.1/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="203,residual.7">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="195" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="196" name="__module.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="197" name="Constant_4311" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="5244388" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="198" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="199" name="Constant_4312" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="5245924" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="200" name="__module.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="207">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="201" name="self.layers.1.fc1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 384" offset="5247460" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="202" name="Convert_16936" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="203" name="self.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 1" offset="5837284" size="1536" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="204" name="Convert_16939" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="205" name="self.layers.1.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="206" name="self.layers.1.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 1" offset="5838820" size="3072" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="207" name="self.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="208" name="self.layers.1.fc1.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="209" name="__module.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="210" name="Constant_4313" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="5841892" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="211" name="__module.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="210">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="212" name="__module.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="211,input.19">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="213" name="self.layers.1.fc2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1536" offset="5848036" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="214" name="Convert_16947" 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="215" name="self.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="6437860" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="216" name="Convert_16950" 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="217" name="self.layers.1.fc2.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="218" name="self.layers.1.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="6438244" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="219" name="self.layers.1.fc2.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="220" name="self.layers.1.fc2.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="221" name="__module.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="222" name="Constant_4314" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="6439012" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="223" name="__module.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="215,input.21">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="224" name="__module.layers.1/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="217,residual.9">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="225" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="226" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="227" name="Constant_4315" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="6440548" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="228" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="229" name="Constant_4316" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="6442084" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="230" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="242,hidden_states.13">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="231" name="Constant_4247" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="6443620" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="232" name="Convert_17123" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="233" name="Constant_4247/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="6591076" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="234" name="Convert_17126" 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="235" name="Constant_4247/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="236" name="Constant_4247/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="6591460" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="237" name="Constant_4247/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="238" name="Constant_4247/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="239" name="Multiply_4232" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="240" name="Constant_4317" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="6592228" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="241" name="__module.layers.2.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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,tensor.13">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="242" name="Constant_4383" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="243" name="__module.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="254">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="244" name="__module.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="245" name="__module.layers.2.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="255">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="246" name="self.layers.2.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="6593764" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="247" name="Convert_17112" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="248" name="self.layers.2.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="6741220" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="249" name="Convert_17115" 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="250" name="self.layers.2.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="251" name="self.layers.2.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="6741604" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="252" name="self.layers.2.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="253" name="self.layers.2.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="254" name="__module.layers.2.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="258,tensor.15">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="255" name="Constant_4384" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="256" name="__module.layers.2.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="260">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="257" name="__module.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="258" name="__module.layers.2.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="261">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="259" name="__module.layers.2.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="271,input.23">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="260" name="__module.layers.2.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="272,input.25">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="261" name="self.layers.2.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="6742372" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="262" name="Convert_17101" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="263" name="self.layers.2.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="6889828" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="264" name="Convert_17104" 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="265" name="self.layers.2.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="266" name="self.layers.2.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="6890212" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="267" name="self.layers.2.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="268" name="self.layers.2.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="269" name="__module.layers.2.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="270" name="Constant_4318" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="6890980" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="271" name="__module.layers.2.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="265,tensor.17">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="272" name="Constant_4385" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="273" name="__module.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="267">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="274" name="__module.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="275" name="__module.layers.2.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="268">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="276" name="__module.layers.2.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="274,attn_output.9">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="277" name="__module.layers.2.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="278" name="__module.layers.2.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="275,attn_output.11">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="279" name="Constant_4386" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="3295948" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="280" name="__module.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="277">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="281" name="self.layers.2.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="6892516" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="282" name="Convert_17134" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="283" name="self.layers.2.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="7039972" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="284" name="Convert_17137" 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="285" name="self.layers.2.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="286" name="self.layers.2.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="7040356" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="287" name="self.layers.2.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="288" name="self.layers.2.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="289" name="__module.layers.2.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="290" name="Constant_4319" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="7041124" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="291" name="__module.layers.2.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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,input.27">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="292" name="__module.layers.2/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="282,residual.11">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="293" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="294" name="__module.layers.2.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="295" name="Constant_4320" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="7042660" 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.layers.2.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="297" name="Constant_4321" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="7044196" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="298" name="__module.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="286">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="299" name="self.layers.2.fc1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 384" offset="7045732" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="300" name="Convert_16958" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="301" name="self.layers.2.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 1" offset="7635556" size="1536" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="302" name="Convert_16961" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="303" name="self.layers.2.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="304" name="self.layers.2.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 1" offset="7637092" size="3072" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="305" name="self.layers.2.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="306" name="self.layers.2.fc1.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="307" name="__module.layers.2.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="308" name="Constant_4322" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="7640164" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="309" name="__module.layers.2.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="289">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="310" name="__module.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="290,input.29">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="311" name="self.layers.2.fc2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1536" offset="7646308" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="312" name="Convert_16969" 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="313" name="self.layers.2.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="8236132" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="314" name="Convert_16972" 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="315" name="self.layers.2.fc2.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="316" name="self.layers.2.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="8236516" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="317" name="self.layers.2.fc2.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="318" name="self.layers.2.fc2.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="319" name="__module.layers.2.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="320" name="Constant_4323" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8237284" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="321" name="__module.layers.2.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="294,input.31">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="322" name="__module.layers.2/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="296,residual.13">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="323" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="324" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="325" name="Constant_4324" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8238820" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="326" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="327" name="Constant_4325" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8240356" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="328" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="321,hidden_states.19">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="329" name="Constant_4250" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="8241892" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="330" name="Convert_17167" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="331" name="Constant_4250/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="8389348" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="332" name="Convert_17170" 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="333" name="Constant_4250/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="334" name="Constant_4250/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="8389732" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="335" name="Constant_4250/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="336" name="Constant_4250/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="337" name="Multiply_4236" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="338" name="Constant_4326" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8390500" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="339" name="__module.layers.3.self_attn/aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="331,tensor.19">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="340" name="Constant_4387" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="341" name="__module.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="333">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="342" name="__module.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="343" name="__module.layers.3.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="334">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="344" name="self.layers.3.self_attn.k_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="8392036" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="345" name="Convert_17156" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="346" name="self.layers.3.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="8539492" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="347" name="Convert_17159" 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="348" name="self.layers.3.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="349" name="self.layers.3.self_attn.k_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="8539876" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="350" name="self.layers.3.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="351" name="self.layers.3.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="352" name="__module.layers.3.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="337,tensor.21">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="353" name="Constant_4388" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="354" name="__module.layers.3.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="339">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="355" name="__module.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="356" name="__module.layers.3.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="340">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="357" name="__module.layers.3.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="350,input.33">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="358" name="__module.layers.3.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
+			<data axis="-1" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="351,input.35">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="359" name="self.layers.3.self_attn.v_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="8540644" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="360" name="Convert_17145" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="361" name="self.layers.3.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="8688100" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="362" name="Convert_17148" 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="363" name="self.layers.3.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="364" name="self.layers.3.self_attn.v_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="8688484" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="365" name="self.layers.3.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="366" name="self.layers.3.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="367" name="__module.layers.3.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="368" name="Constant_4327" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8689252" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="369" name="__module.layers.3.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="344,tensor">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="370" name="Constant_4389" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="2997148" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="371" name="__module.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="346">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="372" name="__module.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="373" name="__module.layers.3.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="347">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="374" name="__module.layers.3.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>1500</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="353,attn_output.13">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="375" name="__module.layers.3.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2997180" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="376" name="__module.layers.3.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>6</dim>
+					<dim>1500</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="354,attn_output">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="377" name="Constant_4390" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="3295948" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="378" name="__module.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>6</dim>
+					<dim>64</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="356">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="379" name="self.layers.3.self_attn.out_proj.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 384" offset="8690788" size="147456" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="380" name="Convert_17178" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="381" name="self.layers.3.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="8838244" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="382" name="Convert_17181" 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="383" name="self.layers.3.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="384" name="self.layers.3.self_attn.out_proj.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="8838628" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="385" name="self.layers.3.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</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>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="386" name="self.layers.3.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>384</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="387" name="__module.layers.3.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="388" name="Constant_4328" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8839396" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="389" name="__module.layers.3.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="359,input.37">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="390" name="__module.layers.3/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="361,residual">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="391" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="392" name="__module.layers.3.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="393" name="Constant_4329" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8840932" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="394" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="395" name="Constant_4330" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="8842468" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="396" name="__module.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="365">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="397" name="self.layers.3.fc1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 384" offset="8844004" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="398" name="Convert_16980" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="399" name="self.layers.3.fc1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="1536, 1" offset="9433828" size="1536" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="400" name="Convert_16983" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="401" name="self.layers.3.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="402" name="self.layers.3.fc1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1536, 1" offset="9435364" size="3072" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="403" name="self.layers.3.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1536</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="404" name="self.layers.3.fc1.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="405" name="__module.layers.3.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="406" name="Constant_4331" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1536" offset="9438436" size="6144" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="407" name="__module.layers.3.fc1/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="368">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="408" name="__module.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="369,input.39">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="409" name="self.layers.3.fc2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1536" offset="9444580" size="589824" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="410" name="Convert_16991" 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="411" name="self.layers.3.fc2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="384, 1" offset="10034404" size="384" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="412" name="Convert_16994" 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="413" name="self.layers.3.fc2.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="414" name="self.layers.3.fc2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="384, 1" offset="10034788" size="768" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>384</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="415" name="self.layers.3.fc2.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="416" name="self.layers.3.fc2.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="417" name="__module.layers.3.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="418" name="Constant_4332" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="10035556" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="419" name="__module.layers.3.fc2/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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="373,input">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="420" name="__module.layers.3/aten::add/Add_1" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="375">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="421" name="__module.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="2843928" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="422" name="__module.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="423" name="Constant_4333" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="10037092" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="424" name="__module.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="425" name="Constant_4334" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 384" offset="10038628" size="1536" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="426" name="__module.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</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>1500</dim>
+					<dim>384</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="427" name="Result_2149" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1500</dim>
+					<dim>384</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="9" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="5" 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="5" to-port="1" />
+		<edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
+		<edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
+		<edge from-layer="7" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="8" from-port="1" to-layer="9" to-port="1" />
+		<edge from-layer="9" from-port="2" to-layer="11" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="12" to-port="0" />
+		<edge from-layer="12" from-port="1" to-layer="21" to-port="0" />
+		<edge from-layer="13" from-port="0" to-layer="14" to-port="0" />
+		<edge from-layer="14" from-port="1" to-layer="17" to-port="0" />
+		<edge from-layer="15" from-port="0" to-layer="16" to-port="0" />
+		<edge from-layer="16" from-port="1" to-layer="17" to-port="1" />
+		<edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="20" to-port="0" />
+		<edge from-layer="20" from-port="1" to-layer="21" to-port="1" />
+		<edge from-layer="21" from-port="2" to-layer="23" to-port="0" />
+		<edge from-layer="22" from-port="0" to-layer="23" to-port="1" />
+		<edge from-layer="23" from-port="2" to-layer="24" to-port="0" />
+		<edge from-layer="24" from-port="1" to-layer="26" to-port="0" />
+		<edge from-layer="25" from-port="0" to-layer="26" to-port="1" />
+		<edge from-layer="26" from-port="2" to-layer="28" to-port="0" />
+		<edge from-layer="27" from-port="0" to-layer="28" to-port="1" />
+		<edge from-layer="28" from-port="2" to-layer="30" to-port="0" />
+		<edge from-layer="28" from-port="2" to-layer="96" to-port="0" />
+		<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
+		<edge from-layer="30" from-port="2" to-layer="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="34" to-port="0" />
+		<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
+		<edge from-layer="34" from-port="2" to-layer="58" to-port="0" />
+		<edge from-layer="34" from-port="2" to-layer="73" to-port="0" />
+		<edge from-layer="34" from-port="2" to-layer="43" to-port="0" />
+		<edge from-layer="35" from-port="0" to-layer="36" to-port="0" />
+		<edge from-layer="36" from-port="1" to-layer="39" to-port="0" />
+		<edge from-layer="37" from-port="0" to-layer="38" to-port="0" />
+		<edge from-layer="38" from-port="1" to-layer="39" to-port="1" />
+		<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
+		<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
+		<edge from-layer="41" from-port="2" to-layer="42" to-port="0" />
+		<edge from-layer="42" from-port="1" to-layer="43" to-port="1" />
+		<edge from-layer="43" from-port="2" to-layer="45" to-port="0" />
+		<edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
+		<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
+		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
+		<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
+		<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
+		<edge from-layer="49" from-port="2" to-layer="63" to-port="0" />
+		<edge from-layer="50" from-port="0" to-layer="51" to-port="0" />
+		<edge from-layer="51" from-port="1" to-layer="54" to-port="0" />
+		<edge from-layer="52" from-port="0" to-layer="53" to-port="0" />
+		<edge from-layer="53" from-port="1" to-layer="54" to-port="1" />
+		<edge from-layer="54" from-port="2" to-layer="56" to-port="0" />
+		<edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
+		<edge from-layer="56" from-port="2" to-layer="57" to-port="0" />
+		<edge from-layer="57" from-port="1" to-layer="58" to-port="1" />
+		<edge from-layer="58" from-port="2" to-layer="60" to-port="0" />
+		<edge from-layer="59" from-port="0" to-layer="60" to-port="1" />
+		<edge from-layer="60" from-port="2" to-layer="62" to-port="0" />
+		<edge from-layer="61" from-port="0" to-layer="62" to-port="1" />
+		<edge from-layer="62" from-port="2" to-layer="63" to-port="1" />
+		<edge from-layer="63" from-port="2" to-layer="64" to-port="0" />
+		<edge from-layer="64" from-port="1" to-layer="80" to-port="0" />
+		<edge from-layer="65" from-port="0" to-layer="66" to-port="0" />
+		<edge from-layer="66" from-port="1" to-layer="69" to-port="0" />
+		<edge from-layer="67" from-port="0" to-layer="68" to-port="0" />
+		<edge from-layer="68" from-port="1" to-layer="69" to-port="1" />
+		<edge from-layer="69" from-port="2" to-layer="71" to-port="0" />
+		<edge from-layer="70" from-port="0" to-layer="71" to-port="1" />
+		<edge from-layer="71" from-port="2" to-layer="72" to-port="0" />
+		<edge from-layer="72" from-port="1" to-layer="73" to-port="1" />
+		<edge from-layer="73" from-port="2" to-layer="75" to-port="0" />
+		<edge from-layer="74" from-port="0" to-layer="75" to-port="1" />
+		<edge from-layer="75" from-port="2" to-layer="77" to-port="0" />
+		<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
+		<edge from-layer="77" from-port="2" to-layer="79" to-port="0" />
+		<edge from-layer="78" from-port="0" to-layer="79" to-port="1" />
+		<edge from-layer="79" from-port="2" to-layer="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="93" to-port="0" />
+		<edge from-layer="85" from-port="0" to-layer="86" to-port="0" />
+		<edge from-layer="86" from-port="1" to-layer="89" to-port="0" />
+		<edge from-layer="87" from-port="0" to-layer="88" to-port="0" />
+		<edge from-layer="88" from-port="1" to-layer="89" to-port="1" />
+		<edge from-layer="89" from-port="2" to-layer="91" to-port="0" />
+		<edge from-layer="90" from-port="0" to-layer="91" to-port="1" />
+		<edge from-layer="91" from-port="2" to-layer="92" to-port="0" />
+		<edge from-layer="92" from-port="1" 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="1" />
+		<edge from-layer="96" from-port="2" to-layer="126" to-port="0" />
+		<edge from-layer="96" from-port="2" to-layer="98" to-port="0" />
+		<edge from-layer="97" from-port="0" to-layer="98" to-port="1" />
+		<edge from-layer="98" from-port="2" to-layer="100" to-port="0" />
+		<edge from-layer="99" from-port="0" to-layer="100" to-port="1" />
+		<edge from-layer="100" from-port="2" to-layer="102" to-port="0" />
+		<edge from-layer="101" from-port="0" to-layer="102" to-port="1" />
+		<edge from-layer="102" from-port="2" to-layer="111" to-port="0" />
+		<edge from-layer="103" from-port="0" to-layer="104" to-port="0" />
+		<edge from-layer="104" from-port="1" to-layer="107" to-port="0" />
+		<edge from-layer="105" from-port="0" to-layer="106" to-port="0" />
+		<edge from-layer="106" from-port="1" to-layer="107" to-port="1" />
+		<edge from-layer="107" from-port="2" to-layer="109" to-port="0" />
+		<edge from-layer="108" from-port="0" to-layer="109" to-port="1" />
+		<edge from-layer="109" from-port="2" to-layer="110" to-port="0" />
+		<edge from-layer="110" from-port="1" to-layer="111" to-port="1" />
+		<edge from-layer="111" from-port="2" to-layer="113" to-port="0" />
+		<edge from-layer="112" from-port="0" to-layer="113" to-port="1" />
+		<edge from-layer="113" from-port="2" to-layer="114" to-port="0" />
+		<edge from-layer="114" from-port="1" to-layer="123" to-port="0" />
+		<edge from-layer="115" from-port="0" to-layer="116" to-port="0" />
+		<edge from-layer="116" from-port="1" to-layer="119" to-port="0" />
+		<edge from-layer="117" from-port="0" to-layer="118" to-port="0" />
+		<edge from-layer="118" from-port="1" to-layer="119" to-port="1" />
+		<edge from-layer="119" from-port="2" 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="0" />
+		<edge from-layer="122" from-port="1" to-layer="123" to-port="1" />
+		<edge from-layer="123" from-port="2" 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="2" to-layer="126" to-port="1" />
+		<edge from-layer="126" from-port="2" to-layer="128" to-port="0" />
+		<edge from-layer="126" from-port="2" to-layer="194" 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="130" to-port="0" />
+		<edge from-layer="129" from-port="0" to-layer="130" to-port="1" />
+		<edge from-layer="130" from-port="2" to-layer="132" to-port="0" />
+		<edge from-layer="131" from-port="0" to-layer="132" to-port="1" />
+		<edge from-layer="132" from-port="2" to-layer="171" to-port="0" />
+		<edge from-layer="132" from-port="2" to-layer="156" to-port="0" />
+		<edge from-layer="132" from-port="2" to-layer="141" to-port="0" />
+		<edge from-layer="133" from-port="0" to-layer="134" to-port="0" />
+		<edge from-layer="134" from-port="1" to-layer="137" to-port="0" />
+		<edge from-layer="135" from-port="0" to-layer="136" to-port="0" />
+		<edge from-layer="136" from-port="1" to-layer="137" to-port="1" />
+		<edge from-layer="137" from-port="2" to-layer="139" to-port="0" />
+		<edge from-layer="138" from-port="0" to-layer="139" to-port="1" />
+		<edge from-layer="139" from-port="2" to-layer="140" to-port="0" />
+		<edge from-layer="140" from-port="1" to-layer="141" to-port="1" />
+		<edge from-layer="141" from-port="2" to-layer="143" to-port="0" />
+		<edge from-layer="142" from-port="0" to-layer="143" to-port="1" />
+		<edge from-layer="143" from-port="2" to-layer="145" to-port="0" />
+		<edge from-layer="144" from-port="0" to-layer="145" to-port="1" />
+		<edge from-layer="145" from-port="2" to-layer="147" to-port="0" />
+		<edge from-layer="146" from-port="0" to-layer="147" to-port="1" />
+		<edge from-layer="147" from-port="2" to-layer="161" to-port="0" />
+		<edge from-layer="148" from-port="0" to-layer="149" to-port="0" />
+		<edge from-layer="149" from-port="1" to-layer="152" to-port="0" />
+		<edge from-layer="150" from-port="0" to-layer="151" to-port="0" />
+		<edge from-layer="151" from-port="1" to-layer="152" to-port="1" />
+		<edge from-layer="152" from-port="2" to-layer="154" to-port="0" />
+		<edge from-layer="153" from-port="0" to-layer="154" to-port="1" />
+		<edge from-layer="154" from-port="2" to-layer="155" to-port="0" />
+		<edge from-layer="155" from-port="1" to-layer="156" to-port="1" />
+		<edge from-layer="156" from-port="2" to-layer="158" to-port="0" />
+		<edge from-layer="157" from-port="0" to-layer="158" to-port="1" />
+		<edge from-layer="158" from-port="2" to-layer="160" to-port="0" />
+		<edge from-layer="159" from-port="0" to-layer="160" to-port="1" />
+		<edge from-layer="160" from-port="2" to-layer="161" to-port="1" />
+		<edge from-layer="161" from-port="2" to-layer="162" to-port="0" />
+		<edge from-layer="162" from-port="1" to-layer="178" to-port="0" />
+		<edge from-layer="163" from-port="0" to-layer="164" to-port="0" />
+		<edge from-layer="164" from-port="1" to-layer="167" to-port="0" />
+		<edge from-layer="165" from-port="0" to-layer="166" to-port="0" />
+		<edge from-layer="166" from-port="1" to-layer="167" to-port="1" />
+		<edge from-layer="167" from-port="2" to-layer="169" to-port="0" />
+		<edge from-layer="168" from-port="0" to-layer="169" to-port="1" />
+		<edge from-layer="169" from-port="2" to-layer="170" to-port="0" />
+		<edge from-layer="170" from-port="1" to-layer="171" to-port="1" />
+		<edge from-layer="171" from-port="2" to-layer="173" to-port="0" />
+		<edge from-layer="172" from-port="0" to-layer="173" to-port="1" />
+		<edge from-layer="173" from-port="2" to-layer="175" to-port="0" />
+		<edge from-layer="174" from-port="0" to-layer="175" to-port="1" />
+		<edge from-layer="175" from-port="2" to-layer="177" to-port="0" />
+		<edge from-layer="176" from-port="0" to-layer="177" to-port="1" />
+		<edge from-layer="177" from-port="2" to-layer="178" to-port="1" />
+		<edge from-layer="178" from-port="2" to-layer="180" to-port="0" />
+		<edge from-layer="179" from-port="0" to-layer="180" to-port="1" />
+		<edge from-layer="180" from-port="2" to-layer="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="191" to-port="0" />
+		<edge from-layer="183" from-port="0" to-layer="184" to-port="0" />
+		<edge from-layer="184" from-port="1" to-layer="187" to-port="0" />
+		<edge from-layer="185" from-port="0" to-layer="186" to-port="0" />
+		<edge from-layer="186" from-port="1" 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="190" to-port="0" />
+		<edge from-layer="190" from-port="1" to-layer="191" to-port="1" />
+		<edge from-layer="191" from-port="2" to-layer="193" to-port="0" />
+		<edge from-layer="192" from-port="0" to-layer="193" to-port="1" />
+		<edge from-layer="193" from-port="2" to-layer="194" to-port="1" />
+		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
+		<edge from-layer="194" from-port="2" to-layer="224" 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="200" to-port="0" />
+		<edge from-layer="199" from-port="0" to-layer="200" to-port="1" />
+		<edge from-layer="200" from-port="2" to-layer="209" to-port="0" />
+		<edge from-layer="201" from-port="0" to-layer="202" to-port="0" />
+		<edge from-layer="202" from-port="1" to-layer="205" to-port="0" />
+		<edge from-layer="203" from-port="0" to-layer="204" to-port="0" />
+		<edge from-layer="204" from-port="1" to-layer="205" to-port="1" />
+		<edge from-layer="205" from-port="2" to-layer="207" to-port="0" />
+		<edge from-layer="206" from-port="0" to-layer="207" to-port="1" />
+		<edge from-layer="207" from-port="2" to-layer="208" to-port="0" />
+		<edge from-layer="208" from-port="1" to-layer="209" to-port="1" />
+		<edge from-layer="209" from-port="2" to-layer="211" to-port="0" />
+		<edge from-layer="210" from-port="0" to-layer="211" to-port="1" />
+		<edge from-layer="211" from-port="2" to-layer="212" to-port="0" />
+		<edge from-layer="212" from-port="1" to-layer="221" to-port="0" />
+		<edge from-layer="213" from-port="0" to-layer="214" to-port="0" />
+		<edge from-layer="214" from-port="1" to-layer="217" to-port="0" />
+		<edge from-layer="215" from-port="0" 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="220" to-port="0" />
+		<edge from-layer="220" from-port="1" 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="224" to-port="1" />
+		<edge from-layer="224" from-port="2" to-layer="226" to-port="0" />
+		<edge from-layer="224" from-port="2" to-layer="292" to-port="0" />
+		<edge from-layer="225" from-port="0" to-layer="226" to-port="1" />
+		<edge from-layer="226" from-port="2" to-layer="228" to-port="0" />
+		<edge from-layer="227" from-port="0" 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="254" to-port="0" />
+		<edge from-layer="230" from-port="2" to-layer="269" to-port="0" />
+		<edge from-layer="230" from-port="2" to-layer="239" to-port="0" />
+		<edge from-layer="231" from-port="0" to-layer="232" to-port="0" />
+		<edge from-layer="232" from-port="1" to-layer="235" to-port="0" />
+		<edge from-layer="233" from-port="0" to-layer="234" to-port="0" />
+		<edge from-layer="234" from-port="1" to-layer="235" to-port="1" />
+		<edge from-layer="235" from-port="2" to-layer="237" to-port="0" />
+		<edge from-layer="236" from-port="0" to-layer="237" to-port="1" />
+		<edge from-layer="237" from-port="2" to-layer="238" to-port="0" />
+		<edge from-layer="238" from-port="1" to-layer="239" to-port="1" />
+		<edge from-layer="239" from-port="2" to-layer="241" to-port="0" />
+		<edge from-layer="240" from-port="0" to-layer="241" to-port="1" />
+		<edge from-layer="241" from-port="2" to-layer="243" to-port="0" />
+		<edge from-layer="242" from-port="0" to-layer="243" to-port="1" />
+		<edge from-layer="243" from-port="2" to-layer="245" to-port="0" />
+		<edge from-layer="244" from-port="0" to-layer="245" to-port="1" />
+		<edge from-layer="245" from-port="2" to-layer="259" to-port="0" />
+		<edge from-layer="246" from-port="0" to-layer="247" to-port="0" />
+		<edge from-layer="247" from-port="1" to-layer="250" to-port="0" />
+		<edge from-layer="248" from-port="0" to-layer="249" to-port="0" />
+		<edge from-layer="249" from-port="1" to-layer="250" to-port="1" />
+		<edge from-layer="250" from-port="2" to-layer="252" to-port="0" />
+		<edge from-layer="251" from-port="0" to-layer="252" to-port="1" />
+		<edge from-layer="252" from-port="2" to-layer="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="1" />
+		<edge from-layer="259" from-port="2" to-layer="260" to-port="0" />
+		<edge from-layer="260" from-port="1" to-layer="276" to-port="0" />
+		<edge from-layer="261" from-port="0" to-layer="262" to-port="0" />
+		<edge from-layer="262" from-port="1" to-layer="265" to-port="0" />
+		<edge from-layer="263" from-port="0" to-layer="264" to-port="0" />
+		<edge from-layer="264" from-port="1" 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="268" to-port="0" />
+		<edge from-layer="268" from-port="1" to-layer="269" to-port="1" />
+		<edge from-layer="269" from-port="2" to-layer="271" to-port="0" />
+		<edge from-layer="270" from-port="0" to-layer="271" to-port="1" />
+		<edge from-layer="271" from-port="2" to-layer="273" to-port="0" />
+		<edge from-layer="272" from-port="0" to-layer="273" to-port="1" />
+		<edge from-layer="273" from-port="2" to-layer="275" to-port="0" />
+		<edge from-layer="274" from-port="0" to-layer="275" to-port="1" />
+		<edge from-layer="275" from-port="2" to-layer="276" to-port="1" />
+		<edge from-layer="276" from-port="2" to-layer="278" to-port="0" />
+		<edge from-layer="277" from-port="0" to-layer="278" to-port="1" />
+		<edge from-layer="278" from-port="2" to-layer="280" to-port="0" />
+		<edge from-layer="279" from-port="0" to-layer="280" to-port="1" />
+		<edge from-layer="280" from-port="2" to-layer="289" to-port="0" />
+		<edge from-layer="281" from-port="0" to-layer="282" to-port="0" />
+		<edge from-layer="282" from-port="1" to-layer="285" to-port="0" />
+		<edge from-layer="283" from-port="0" to-layer="284" to-port="0" />
+		<edge from-layer="284" from-port="1" to-layer="285" to-port="1" />
+		<edge from-layer="285" from-port="2" to-layer="287" to-port="0" />
+		<edge from-layer="286" from-port="0" to-layer="287" to-port="1" />
+		<edge from-layer="287" from-port="2" to-layer="288" to-port="0" />
+		<edge from-layer="288" from-port="1" to-layer="289" to-port="1" />
+		<edge from-layer="289" from-port="2" to-layer="291" to-port="0" />
+		<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
+		<edge from-layer="291" from-port="2" to-layer="292" to-port="1" />
+		<edge from-layer="292" from-port="2" to-layer="294" to-port="0" />
+		<edge from-layer="292" from-port="2" to-layer="322" to-port="0" />
+		<edge from-layer="293" from-port="0" to-layer="294" to-port="1" />
+		<edge from-layer="294" from-port="2" to-layer="296" to-port="0" />
+		<edge from-layer="295" from-port="0" to-layer="296" to-port="1" />
+		<edge from-layer="296" from-port="2" to-layer="298" to-port="0" />
+		<edge from-layer="297" from-port="0" to-layer="298" to-port="1" />
+		<edge from-layer="298" from-port="2" to-layer="307" to-port="0" />
+		<edge from-layer="299" from-port="0" to-layer="300" to-port="0" />
+		<edge from-layer="300" from-port="1" to-layer="303" to-port="0" />
+		<edge from-layer="301" from-port="0" to-layer="302" to-port="0" />
+		<edge from-layer="302" from-port="1" to-layer="303" to-port="1" />
+		<edge from-layer="303" from-port="2" to-layer="305" to-port="0" />
+		<edge from-layer="304" from-port="0" to-layer="305" to-port="1" />
+		<edge from-layer="305" from-port="2" to-layer="306" to-port="0" />
+		<edge from-layer="306" from-port="1" to-layer="307" to-port="1" />
+		<edge from-layer="307" from-port="2" to-layer="309" to-port="0" />
+		<edge from-layer="308" from-port="0" to-layer="309" to-port="1" />
+		<edge from-layer="309" from-port="2" to-layer="310" to-port="0" />
+		<edge from-layer="310" from-port="1" to-layer="319" to-port="0" />
+		<edge from-layer="311" from-port="0" to-layer="312" to-port="0" />
+		<edge from-layer="312" from-port="1" to-layer="315" to-port="0" />
+		<edge from-layer="313" from-port="0" to-layer="314" to-port="0" />
+		<edge from-layer="314" from-port="1" to-layer="315" to-port="1" />
+		<edge from-layer="315" from-port="2" to-layer="317" to-port="0" />
+		<edge from-layer="316" from-port="0" to-layer="317" to-port="1" />
+		<edge from-layer="317" from-port="2" to-layer="318" to-port="0" />
+		<edge from-layer="318" from-port="1" to-layer="319" to-port="1" />
+		<edge from-layer="319" from-port="2" to-layer="321" to-port="0" />
+		<edge from-layer="320" from-port="0" to-layer="321" to-port="1" />
+		<edge from-layer="321" from-port="2" to-layer="322" to-port="1" />
+		<edge from-layer="322" from-port="2" to-layer="390" to-port="0" />
+		<edge from-layer="322" from-port="2" to-layer="324" to-port="0" />
+		<edge from-layer="323" from-port="0" to-layer="324" to-port="1" />
+		<edge from-layer="324" from-port="2" to-layer="326" to-port="0" />
+		<edge from-layer="325" from-port="0" to-layer="326" to-port="1" />
+		<edge from-layer="326" from-port="2" to-layer="328" to-port="0" />
+		<edge from-layer="327" from-port="0" to-layer="328" to-port="1" />
+		<edge from-layer="328" from-port="2" to-layer="352" to-port="0" />
+		<edge from-layer="328" from-port="2" to-layer="367" to-port="0" />
+		<edge from-layer="328" from-port="2" to-layer="337" to-port="0" />
+		<edge from-layer="329" from-port="0" to-layer="330" to-port="0" />
+		<edge from-layer="330" from-port="1" to-layer="333" to-port="0" />
+		<edge from-layer="331" from-port="0" to-layer="332" to-port="0" />
+		<edge from-layer="332" from-port="1" to-layer="333" to-port="1" />
+		<edge from-layer="333" from-port="2" to-layer="335" to-port="0" />
+		<edge from-layer="334" from-port="0" to-layer="335" to-port="1" />
+		<edge from-layer="335" from-port="2" to-layer="336" to-port="0" />
+		<edge from-layer="336" from-port="1" to-layer="337" to-port="1" />
+		<edge from-layer="337" from-port="2" to-layer="339" to-port="0" />
+		<edge from-layer="338" from-port="0" to-layer="339" to-port="1" />
+		<edge from-layer="339" from-port="2" to-layer="341" to-port="0" />
+		<edge from-layer="340" from-port="0" to-layer="341" to-port="1" />
+		<edge from-layer="341" from-port="2" to-layer="343" to-port="0" />
+		<edge from-layer="342" from-port="0" to-layer="343" to-port="1" />
+		<edge from-layer="343" from-port="2" to-layer="357" to-port="0" />
+		<edge from-layer="344" from-port="0" to-layer="345" to-port="0" />
+		<edge from-layer="345" from-port="1" to-layer="348" to-port="0" />
+		<edge from-layer="346" from-port="0" 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="351" to-port="0" />
+		<edge from-layer="351" from-port="1" 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="356" to-port="0" />
+		<edge from-layer="355" from-port="0" to-layer="356" to-port="1" />
+		<edge from-layer="356" from-port="2" to-layer="357" to-port="1" />
+		<edge from-layer="357" from-port="2" to-layer="358" to-port="0" />
+		<edge from-layer="358" from-port="1" to-layer="374" to-port="0" />
+		<edge from-layer="359" from-port="0" to-layer="360" to-port="0" />
+		<edge from-layer="360" from-port="1" to-layer="363" to-port="0" />
+		<edge from-layer="361" from-port="0" to-layer="362" to-port="0" />
+		<edge from-layer="362" from-port="1" to-layer="363" to-port="1" />
+		<edge from-layer="363" from-port="2" to-layer="365" to-port="0" />
+		<edge from-layer="364" from-port="0" to-layer="365" to-port="1" />
+		<edge from-layer="365" from-port="2" to-layer="366" to-port="0" />
+		<edge from-layer="366" from-port="1" to-layer="367" to-port="1" />
+		<edge from-layer="367" from-port="2" to-layer="369" to-port="0" />
+		<edge from-layer="368" from-port="0" to-layer="369" to-port="1" />
+		<edge from-layer="369" from-port="2" to-layer="371" to-port="0" />
+		<edge from-layer="370" from-port="0" to-layer="371" to-port="1" />
+		<edge from-layer="371" from-port="2" to-layer="373" to-port="0" />
+		<edge from-layer="372" from-port="0" to-layer="373" to-port="1" />
+		<edge from-layer="373" from-port="2" to-layer="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="378" to-port="0" />
+		<edge from-layer="377" from-port="0" to-layer="378" to-port="1" />
+		<edge from-layer="378" from-port="2" to-layer="387" to-port="0" />
+		<edge from-layer="379" from-port="0" to-layer="380" to-port="0" />
+		<edge from-layer="380" from-port="1" to-layer="383" to-port="0" />
+		<edge from-layer="381" from-port="0" to-layer="382" to-port="0" />
+		<edge from-layer="382" from-port="1" to-layer="383" to-port="1" />
+		<edge from-layer="383" from-port="2" to-layer="385" to-port="0" />
+		<edge from-layer="384" from-port="0" to-layer="385" to-port="1" />
+		<edge from-layer="385" from-port="2" to-layer="386" to-port="0" />
+		<edge from-layer="386" from-port="1" to-layer="387" to-port="1" />
+		<edge from-layer="387" from-port="2" to-layer="389" to-port="0" />
+		<edge from-layer="388" from-port="0" to-layer="389" to-port="1" />
+		<edge from-layer="389" from-port="2" to-layer="390" to-port="1" />
+		<edge from-layer="390" from-port="2" to-layer="392" to-port="0" />
+		<edge from-layer="390" from-port="2" to-layer="420" 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="394" to-port="0" />
+		<edge from-layer="393" from-port="0" 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="405" to-port="0" />
+		<edge from-layer="397" from-port="0" to-layer="398" to-port="0" />
+		<edge from-layer="398" from-port="1" to-layer="401" to-port="0" />
+		<edge from-layer="399" from-port="0" to-layer="400" to-port="0" />
+		<edge from-layer="400" from-port="1" to-layer="401" to-port="1" />
+		<edge from-layer="401" from-port="2" to-layer="403" to-port="0" />
+		<edge from-layer="402" from-port="0" to-layer="403" to-port="1" />
+		<edge from-layer="403" from-port="2" to-layer="404" to-port="0" />
+		<edge from-layer="404" from-port="1" to-layer="405" to-port="1" />
+		<edge from-layer="405" from-port="2" to-layer="407" to-port="0" />
+		<edge from-layer="406" from-port="0" to-layer="407" to-port="1" />
+		<edge from-layer="407" from-port="2" to-layer="408" to-port="0" />
+		<edge from-layer="408" from-port="1" to-layer="417" to-port="0" />
+		<edge from-layer="409" from-port="0" to-layer="410" to-port="0" />
+		<edge from-layer="410" from-port="1" to-layer="413" to-port="0" />
+		<edge from-layer="411" from-port="0" to-layer="412" to-port="0" />
+		<edge from-layer="412" from-port="1" 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="416" to-port="0" />
+		<edge from-layer="416" from-port="1" to-layer="417" to-port="1" />
+		<edge from-layer="417" from-port="2" to-layer="419" to-port="0" />
+		<edge from-layer="418" from-port="0" to-layer="419" to-port="1" />
+		<edge from-layer="419" from-port="2" to-layer="420" to-port="1" />
+		<edge from-layer="420" from-port="2" to-layer="422" to-port="0" />
+		<edge from-layer="421" from-port="0" 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" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2024.5.0-16901-32aaa2fbd96" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<weight_compression>
+				<advanced_parameters value="{'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_asym" />
+				<ratio value="1" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<optimum_intel_version value="1.20.0.dev0+2559620" />
+			<optimum_version value="1.23.1" />
+			<pytorch_version value="2.5.0" />
+			<transformers_version value="4.45.2" />
+		</optimum>
+	</rt_info>
+</net>