openvino_decoder_model.xml

<?xml version="1.0"?>
<net name="Model3" version="11">
	<layers>
		<layer id="0" name="decoder_input_ids" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="input_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="Parameter_27858" type="Parameter" version="opset1">
			<data shape="?,?,1280" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="encoder_hidden_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="beam_idx" type="Parameter" version="opset1">
			<data shape="?" element_type="i32" />
			<output>
				<port id="0" precision="I32" names="beam_idx">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="0" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Convert_1085787" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="1638400" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="Convert_1085790" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="1639680" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="__module.model.decoder.layers.2.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="458">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="Constant_38548" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="__module.model.decoder.layers.2.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="460,key_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="466">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="ReadValue_40565" type="ReadValue" version="opset6">
			<data variable_id="466" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="1642288" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="18" name="Convert_1090854" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="3280688" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="20" name="Convert_1090857" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="21" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="3281968" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="24" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="__module.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="26" name="Constant_37763" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="3284528" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="27" name="__module.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="341">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="Constant_38541" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="29" name="__module.model.decoder.layers.1.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="343,value_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="31" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="346">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="ReadValue_40563" type="ReadValue" version="opset6">
			<data variable_id="346" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="3289648" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="Convert_1095921" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="4928048" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="Convert_1095924" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="4929328" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="__module.model.decoder.layers.3.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="Constant_37795" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="4931888" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="__module.model.decoder.layers.3.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="585">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="Constant_38557" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="__module.model.decoder.layers.3.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="587,value_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="590">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="ReadValue_40561" type="ReadValue" version="opset6">
			<data variable_id="590" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="4937008" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="Convert_1100988" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="6575408" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="Convert_1100991" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="6576688" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="__module.model.decoder.layers.1.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="336">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="Constant_38540" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="__module.model.decoder.layers.1.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="338,key_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="60" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="344">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="ReadValue_40559" type="ReadValue" version="opset6">
			<data variable_id="344" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="6579248" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="Convert_1106055" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="8217648" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Convert_1106058" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="8218928" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="70" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="__module.model.decoder.layers.0.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="214">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="Constant_38532" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="73" name="__module.model.decoder.layers.0.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="216,key_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="222">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="ReadValue_40557" type="ReadValue" version="opset6">
			<data variable_id="222" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="8221488" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="Convert_1111122" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="9859888" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="Convert_1111125" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="82" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="9861168" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="__module.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="Constant_37747" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="9863728" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="__module.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="219">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="Constant_38533" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.model.decoder.layers.0.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="221,value_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="224">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="ReadValue_40555" type="ReadValue" version="opset6">
			<data variable_id="224" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="9868848" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="Convert_1116189" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="11507248" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="Convert_1116192" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="11508528" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="__module.model.decoder.layers.2.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="Constant_37779" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="11511088" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="__module.model.decoder.layers.2.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="463">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="Constant_38549" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="__module.model.decoder.layers.2.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="465,value_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="468">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="ReadValue_40553" type="ReadValue" version="opset6">
			<data variable_id="468" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="11516208" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="Convert_1121256" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="13154608" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="Convert_1121259" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="13155888" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="__module.model.decoder.layers.3.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="580">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="Constant_38556" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="__module.model.decoder.layers.3.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="582,key_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="588">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="ReadValue_40551" type="ReadValue" version="opset6">
			<data variable_id="588" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="Constant_40179" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="124" name="ShapeOf_40165" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="Constant_40167" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="Constant_40169" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="127" name="Gather_40170" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="113,148,203,270,325,392,447,514,569,85">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="Constant_40172" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="13158460" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="Constant_40174" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="Constant_40176" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="13158468" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="Concat_40177" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="Broadcast_40180" type="Broadcast" version="opset3">
			<data mode="numpy" />
			<input>
				<port id="0" precision="FP32" />
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="ReadValue_39895" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.3.decoder.valuepresent.3.decoder.value" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.3.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="Constant_39611" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="135" name="Gather_39612" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="self.model.decoder.embed_tokens.weight" type="Const" version="opset1">
			<data element_type="u8" shape="51866, 1280" offset="13158476" size="66388480" />
			<output>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="Convert_1040184" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="self.model.decoder.embed_tokens.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="51866, 1" offset="79546956" size="51866" />
			<output>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="Convert_1040187" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="self.model.decoder.embed_tokens.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="self.model.decoder.embed_tokens.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="51866, 1" offset="79598822" size="103732" />
			<output>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="self.model.decoder.embed_tokens.weight/fq_weights_0" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="self.model.decoder.embed_tokens.weight/fq_weights_0/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="Constant_38526" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="79702554" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="__module.model.decoder/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="89,input.1">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="__module.model.decoder.embed_tokens/aten::embedding/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="__module.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="148" name="__module.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="91,inputs_embeds">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="self.model.decoder.embed_positions.weight" type="Const" version="opset1">
			<data element_type="u8" shape="448, 1280" offset="79702570" size="573440" />
			<output>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="Convert_1247931" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="self.model.decoder.embed_positions.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="448, 1" offset="80276010" size="448" />
			<output>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="Convert_1247934" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="self.model.decoder.embed_positions.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="self.model.decoder.embed_positions.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="448, 1" offset="80276458" size="896" />
			<output>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="self.model.decoder.embed_positions.weight/fq_weights_0" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="self.model.decoder.embed_positions.weight/fq_weights_0/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="ReadValue_39881" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.0.decoder.keypresent.0.decoder.key" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.0.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="Constant_39590" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="159" name="Gather_39591" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="ShapeOf_38134" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="Constant_38135" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="80277354" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="162" name="Constant_38136" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="163" name="Gather_38137" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
				<port id="1" precision="I64" />
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="108,92" />
			</output>
		</layer>
		<layer id="164" name="Constant_38125" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="80277362" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="165" name="Constant_38126" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="166" name="Gather_38127" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64" />
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="86" />
			</output>
		</layer>
		<layer id="167" name="__module.model.decoder/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="94" />
			</output>
		</layer>
		<layer id="168" name="__module.model.decoder/aten::arange/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="80277370" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="169" name="__module.model.decoder/aten::arange/Range" type="Range" version="opset4">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64" />
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="I64" names="96,cache_position">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="48" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" names="48" />
			</output>
		</layer>
		<layer id="171" name="__module.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="115,97">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="Constant_28391" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="80277362" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="__module.model.decoder/prim::ListConstruct/Concat" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="98">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="__module.model.decoder/aten::repeat/Tile" type="Tile" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="99,position_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="__module.model.decoder.embed_positions/aten::index/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="__module.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="177" name="__module.model.decoder.embed_positions/aten::index/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="102,103,positions,positions.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="__module.model.decoder/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="104,input.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="__module.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="180" name="__module.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="181" name="Constant_37737" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="80277378" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="__module.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="Constant_37738" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="80282498" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="__module.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="143,hidden_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="self.model.decoder.layers.0.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="80287618" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="Convert_1136457" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="self.model.decoder.layers.0.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="81926018" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="Convert_1136460" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="self.model.decoder.layers.0.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="self.model.decoder.layers.0.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="81927298" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="self.model.decoder.layers.0.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="self.model.decoder.layers.0.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="193" name="__module.model.decoder.layers.0.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="Constant_37739" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="Multiply_37500" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="196" name="Constant_37740" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="81929862" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.model.decoder.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="153,query_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="198" name="Constant_38527" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.model.decoder.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="155,query_states.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="201" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="156">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="self.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="81934982" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="203" name="Convert_1131390" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="self.model.decoder.layers.0.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="83573382" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="Convert_1131393" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="self.model.decoder.layers.0.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="self.model.decoder.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="83574662" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="self.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="self.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="__module.model.decoder.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="159">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="Constant_38528" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="__module.model.decoder.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="161,key_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="214" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="167">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="__module.model.decoder.layers.0.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.1">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="ReadValue_39883" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.0.decoder.valuepresent.0.decoder.value" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.0.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="217" name="Constant_39593" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="218" name="Gather_39594" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="219" name="self.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="83577222" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="Convert_1126323" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="221" name="self.model.decoder.layers.0.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="85215622" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="222" name="Convert_1126326" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="self.model.decoder.layers.0.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="self.model.decoder.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="85216902" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="self.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="self.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="__module.model.decoder.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="Constant_37741" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="85219462" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="__module.model.decoder.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="164">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="230" name="Constant_38529" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="__module.model.decoder.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="166,value_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="233" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="169">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="__module.model.decoder.layers.0.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.1">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="235" name="__module.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="236" name="Constant_48062" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="85224582" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="Reshape_38153" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="__module.model.decoder/aten::size/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="239" name="__module.model.decoder/aten::size/Gather_4" type="Squeeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I32" />
			</input>
			<output>
				<port id="2" precision="I64" names="106,114" />
			</output>
		</layer>
		<layer id="240" name="__module.model.decoder/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="110,111,kv_length" />
			</output>
		</layer>
		<layer id="241" name="__module.model.decoder/aten::arange/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="80277370" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="242" name="__module.model.decoder/aten::arange/Range_1" type="Range" version="opset4">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I32" />
				<port id="1" precision="I64" />
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="I64" names="119">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="__module.model.decoder/aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="120">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="244" name="49" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="80277362" size="8" />
			<output>
				<port id="0" precision="I64" names="49" />
			</output>
		</layer>
		<layer id="245" name="__module.model.decoder/aten::unsqueeze/Unsqueeze_2" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="121">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="53" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="80277354" size="8" />
			<output>
				<port id="0" precision="I64" names="53" />
			</output>
		</layer>
		<layer id="247" name="__module.model.decoder/aten::unsqueeze/Unsqueeze_3" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="122,123,124,kv_idx">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="248" name="__module.model.decoder/aten::unsqueeze/Unsqueeze_5" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="116,117">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="249" name="59" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="85224590" size="8" />
			<output>
				<port id="0" precision="I64" names="59" />
			</output>
		</layer>
		<layer id="250" name="__module.model.decoder/aten::unsqueeze/Unsqueeze_6" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="118,q_idx">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="__module.model.decoder/aten::le/LessEqual" type="LessEqual" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="125,causal_mask">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="252" name="Constant_35246" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="80277362" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="253" name="Constant_25462" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="254" name="Unsqueeze_25463" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I32" />
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="__module.model.decoder/prim::ListConstruct_1" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="256" name="__module.model.decoder/aten::expand/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="127,mask">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="257" name="__module.model.decoder/aten::to/Convert_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="FP32" names="128" />
			</output>
		</layer>
		<layer id="258" name="__module.model.decoder/aten::to/Convert_2" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="85224598" size="4" />
			<output>
				<port id="0" precision="FP32" names="130" />
			</output>
		</layer>
		<layer id="259" name="__module.model.decoder/aten::where/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="132,176,177,178,298,299,300,420,421,422,542,543,544,attention_mask.3">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="Constant_25710" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="Constant_48063" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="85224582" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="Reshape_38165" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="Add_38168" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="175,297,419,541">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="Constant_25713" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="80277362" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="Constant_25708" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="85224590" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="__module.model.decoder.layers.0.self_attn/aten::slice/Slice_3" type="Slice" version="opset8">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
				<port id="4" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="5" precision="FP32" names="179,301,423,545,attention_mask,attention_mask.5,attention_mask.7,attention_mask.9">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="__module.model.decoder.layers.0.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="85224602" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="268" name="__module.model.decoder.layers.0.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="180,attn_output.1">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="269" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="181">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="Constant_38530" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="272" name="__module.model.decoder.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="184">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="self.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="85224630" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="Convert_1141524" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="self.model.decoder.layers.0.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="86863030" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="Convert_1141527" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="self.model.decoder.layers.0.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="self.model.decoder.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="86864310" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="self.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="self.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="281" name="__module.model.decoder.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="Constant_37742" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="86866870" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="__module.model.decoder.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="188,input.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="__module.model.decoder.layers.0/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="194,input.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="__module.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="__module.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="287" name="Constant_37743" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="86871990" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="__module.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="289" name="Constant_37744" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="86877110" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="__module.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="198,hidden_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="86882230" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="Convert_1146591" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="88520630" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="Convert_1146594" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="88521910" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="__module.model.decoder.layers.0.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="Constant_37745" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="301" name="Multiply_37504" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="Constant_37746" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="88524470" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="__module.model.decoder.layers.0.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="208,query_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="Constant_38531" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="305" name="__module.model.decoder.layers.0.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="210,query_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="211">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="__module.model.decoder.layers.0.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="309" name="__module.model.decoder.layers.0.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="226,attn_output.5">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="227">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="Constant_38534" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="313" name="__module.model.decoder.layers.0.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="230">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="88529590" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="Convert_1151658" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="316" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="90167990" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="Convert_1151661" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="319" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="90169270" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="320" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="__module.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="323" name="Constant_37748" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="90171830" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="324" name="__module.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="234,input.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="325" name="__module.model.decoder.layers.0/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="236,input.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="326" name="__module.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="327" name="__module.model.decoder.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="328" name="Constant_37749" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="90176950" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="329" name="__module.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="330" name="Constant_37750" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="90182070" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="331" name="__module.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="240,input.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="332" name="self.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1280" offset="90187190" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="333" name="Convert_1045251" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="self.model.decoder.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1" offset="96740790" size="5120" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="335" name="Convert_1045254" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="self.model.decoder.layers.0.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="self.model.decoder.layers.0.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 1" offset="96745910" size="10240" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="338" name="self.model.decoder.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="self.model.decoder.layers.0.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="__module.model.decoder.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="Constant_37751" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="96756150" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="__module.model.decoder.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="243,input.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="__module.model.decoder.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="244,input.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="344" name="self.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 5120" offset="96776630" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="345" name="Convert_1050318" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="346" name="self.model.decoder.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="103330230" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="Convert_1050321" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="348" name="self.model.decoder.layers.0.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="self.model.decoder.layers.0.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="103331510" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="350" name="self.model.decoder.layers.0.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="351" name="self.model.decoder.layers.0.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="__module.model.decoder.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="353" name="Constant_37752" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103334070" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="__module.model.decoder.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="248,input.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="355" name="__module.model.decoder.layers.0/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="250,input.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="__module.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="__module.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="358" name="Constant_37753" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103339190" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="__module.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="Constant_37754" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103344310" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="361" name="__module.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="265,hidden_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="362" name="self.model.decoder.layers.1.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="103349430" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="363" name="Convert_1166859" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="self.model.decoder.layers.1.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="104987830" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="365" name="Convert_1166862" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="366" name="self.model.decoder.layers.1.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="367" name="self.model.decoder.layers.1.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="104989110" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="368" name="self.model.decoder.layers.1.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="369" name="self.model.decoder.layers.1.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="370" name="__module.model.decoder.layers.1.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="371" name="Constant_37755" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="372" name="Multiply_37508" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="373" name="Constant_37756" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="104991670" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="374" name="__module.model.decoder.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="275,query_states.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="375" name="Constant_38535" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="376" name="__module.model.decoder.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="277,query_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="377" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="378" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="278">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="379" name="ReadValue_39885" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.1.decoder.keypresent.1.decoder.key" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.1.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="380" name="Constant_39596" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="381" name="Gather_39597" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="382" name="self.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="104996790" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="383" name="Convert_1161792" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="384" name="self.model.decoder.layers.1.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="106635190" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="385" name="Convert_1161795" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="386" name="self.model.decoder.layers.1.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="387" name="self.model.decoder.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="106636470" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="388" name="self.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="389" name="self.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="390" name="__module.model.decoder.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="281">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="391" name="Constant_38536" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="392" name="__module.model.decoder.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="283,key_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="393" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="394" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="289">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="395" name="__module.model.decoder.layers.1.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.5">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="396" name="ReadValue_39887" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.1.decoder.valuepresent.1.decoder.value" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.1.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="397" name="Constant_39599" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="398" name="Gather_39600" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="399" name="self.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="106639030" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="400" name="Convert_1156725" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="401" name="self.model.decoder.layers.1.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="108277430" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="402" name="Convert_1156728" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="403" name="self.model.decoder.layers.1.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="404" name="self.model.decoder.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="108278710" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="405" name="self.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="406" name="self.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="407" name="__module.model.decoder.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="408" name="Constant_37757" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="108281270" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="409" name="__module.model.decoder.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="286">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="410" name="Constant_38537" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="411" name="__module.model.decoder.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="288,value_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="412" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="413" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="291">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="414" name="__module.model.decoder.layers.1.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.5">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="415" name="__module.model.decoder.layers.1.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="302,attn_output.9">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="416" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="417" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="303">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="418" name="Constant_38538" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="419" name="__module.model.decoder.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="306">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="420" name="self.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="108286390" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="421" name="Convert_1171926" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="422" name="self.model.decoder.layers.1.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="109924790" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="423" name="Convert_1171929" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="424" name="self.model.decoder.layers.1.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="425" name="self.model.decoder.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="109926070" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="426" name="self.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="427" name="self.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="428" name="__module.model.decoder.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="429" name="Constant_37758" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="109928630" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="430" name="__module.model.decoder.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="310,input.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="431" name="__module.model.decoder.layers.1/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="316,input.37">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="432" name="__module.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="433" name="__module.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="434" name="Constant_37759" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="109933750" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="435" name="__module.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="436" name="Constant_37760" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="109938870" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="437" name="__module.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="320,hidden_states.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="438" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="109943990" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="439" name="Convert_1176993" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="440" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="111582390" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="441" name="Convert_1176996" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="442" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="443" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="111583670" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="444" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="445" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="446" name="__module.model.decoder.layers.1.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="447" name="Constant_37761" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="448" name="Multiply_37512" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="449" name="Constant_37762" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="111586230" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="450" name="__module.model.decoder.layers.1.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="330,query_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="451" name="Constant_38539" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="452" name="__module.model.decoder.layers.1.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="332,query_states.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="453" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="454" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="333">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="455" name="__module.model.decoder.layers.1.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="456" name="__module.model.decoder.layers.1.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="348,attn_output.13">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="457" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="458" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="349">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="459" name="Constant_38542" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="460" name="__module.model.decoder.layers.1.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="352">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="461" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="111591350" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="462" name="Convert_1182060" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="463" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="113229750" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="464" name="Convert_1182063" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="465" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="466" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="113231030" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="467" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="468" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="469" name="__module.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="470" name="Constant_37764" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="113233590" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="471" name="__module.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="356,input.41">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="472" name="__module.model.decoder.layers.1/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="358,input.43">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="473" name="__module.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="474" name="__module.model.decoder.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="475" name="Constant_37765" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="113238710" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="476" name="__module.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="477" name="Constant_37766" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="113243830" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="478" name="__module.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="362,input.45">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="479" name="self.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1280" offset="113248950" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="480" name="Convert_1055385" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="481" name="self.model.decoder.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1" offset="119802550" size="5120" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="482" name="Convert_1055388" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="483" name="self.model.decoder.layers.1.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="484" name="self.model.decoder.layers.1.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 1" offset="119807670" size="10240" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="485" name="self.model.decoder.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="486" name="self.model.decoder.layers.1.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="487" name="__module.model.decoder.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="488" name="Constant_37767" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="119817910" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="489" name="__module.model.decoder.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="365,input.47">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="490" name="__module.model.decoder.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="366,input.49">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="491" name="self.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 5120" offset="119838390" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="492" name="Convert_1060452" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="493" name="self.model.decoder.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="126391990" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="494" name="Convert_1060455" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="495" name="self.model.decoder.layers.1.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="496" name="self.model.decoder.layers.1.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="126393270" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="497" name="self.model.decoder.layers.1.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="498" name="self.model.decoder.layers.1.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="499" name="__module.model.decoder.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="500" name="Constant_37768" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="126395830" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="501" name="__module.model.decoder.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="370,input.53">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="502" name="__module.model.decoder.layers.1/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="372,input.55">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="503" name="__module.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="504" name="__module.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="505" name="Constant_37769" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="126400950" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="506" name="__module.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="507" name="Constant_37770" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="126406070" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="508" name="__module.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="387,hidden_states.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="509" name="self.model.decoder.layers.2.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="126411190" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="510" name="Convert_1197261" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="511" name="self.model.decoder.layers.2.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="128049590" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="512" name="Convert_1197264" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="513" name="self.model.decoder.layers.2.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="514" name="self.model.decoder.layers.2.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="128050870" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="515" name="self.model.decoder.layers.2.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="516" name="self.model.decoder.layers.2.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="517" name="__module.model.decoder.layers.2.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="518" name="Constant_37771" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="519" name="Multiply_37516" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="520" name="Constant_37772" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="128053430" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="521" name="__module.model.decoder.layers.2.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="397,query_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="522" name="Constant_38543" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="523" name="__module.model.decoder.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="399,query_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="524" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="525" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="400">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="526" name="ReadValue_39889" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.2.decoder.keypresent.2.decoder.key" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.2.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="527" name="Constant_39602" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="528" name="Gather_39603" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="529" name="self.model.decoder.layers.2.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="128058550" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="530" name="Convert_1192194" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="531" name="self.model.decoder.layers.2.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="129696950" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="532" name="Convert_1192197" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="533" name="self.model.decoder.layers.2.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="534" name="self.model.decoder.layers.2.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="129698230" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="535" name="self.model.decoder.layers.2.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="536" name="self.model.decoder.layers.2.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="537" name="__module.model.decoder.layers.2.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="403">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="538" name="Constant_38544" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="539" name="__module.model.decoder.layers.2.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="405,key_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="540" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="541" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="411">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="542" name="__module.model.decoder.layers.2.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.9">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="543" name="ReadValue_39891" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.2.decoder.valuepresent.2.decoder.value" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.2.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="544" name="Constant_39605" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="545" name="Gather_39606" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="546" name="self.model.decoder.layers.2.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="129700790" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="547" name="Convert_1187127" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="548" name="self.model.decoder.layers.2.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="131339190" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="549" name="Convert_1187130" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="550" name="self.model.decoder.layers.2.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="551" name="self.model.decoder.layers.2.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="131340470" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="552" name="self.model.decoder.layers.2.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="553" name="self.model.decoder.layers.2.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="554" name="__module.model.decoder.layers.2.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="555" name="Constant_37773" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="131343030" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="556" name="__module.model.decoder.layers.2.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="408">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="557" name="Constant_38545" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="558" name="__module.model.decoder.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="410,value_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="559" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="560" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="413">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="561" name="__module.model.decoder.layers.2.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.9">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="562" name="__module.model.decoder.layers.2.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="424,attn_output.17">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="563" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="564" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="425">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="565" name="Constant_38546" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="566" name="__module.model.decoder.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="428">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="567" name="self.model.decoder.layers.2.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="131348150" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="568" name="Convert_1202328" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="569" name="self.model.decoder.layers.2.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="132986550" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="570" name="Convert_1202331" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="571" name="self.model.decoder.layers.2.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="572" name="self.model.decoder.layers.2.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="132987830" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="573" name="self.model.decoder.layers.2.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="574" name="self.model.decoder.layers.2.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="575" name="__module.model.decoder.layers.2.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="576" name="Constant_37774" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="132990390" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="577" name="__module.model.decoder.layers.2.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="432,input.59">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="578" name="__module.model.decoder.layers.2/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="438,input.61">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="579" name="__module.model.decoder.layers.2.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="580" name="__module.model.decoder.layers.2.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="581" name="Constant_37775" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="132995510" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="582" name="__module.model.decoder.layers.2.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="583" name="Constant_37776" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="133000630" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="584" name="__module.model.decoder.layers.2.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="442,hidden_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="585" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="133005750" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="586" name="Convert_1207395" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="587" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="134644150" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="588" name="Convert_1207398" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="589" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="590" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="134645430" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="591" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="592" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="593" name="__module.model.decoder.layers.2.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="594" name="Constant_37777" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="595" name="Multiply_37520" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="596" name="Constant_37778" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="134647990" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="597" name="__module.model.decoder.layers.2.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="452,query_states.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="598" name="Constant_38547" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="599" name="__module.model.decoder.layers.2.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="454,query_states.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="600" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="601" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="455">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="602" name="__module.model.decoder.layers.2.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="603" name="__module.model.decoder.layers.2.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="470,attn_output.21">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="604" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="605" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="471">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="606" name="Constant_38550" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="607" name="__module.model.decoder.layers.2.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="474">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="608" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="134653110" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="609" name="Convert_1212462" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="610" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="136291510" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="611" name="Convert_1212465" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="612" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="613" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="136292790" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="614" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="615" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="616" name="__module.model.decoder.layers.2.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="617" name="Constant_37780" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="136295350" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="618" name="__module.model.decoder.layers.2.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="478,input.65">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="619" name="__module.model.decoder.layers.2/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="480,input.67">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="620" name="__module.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="621" name="__module.model.decoder.layers.2.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="622" name="Constant_37781" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="136300470" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="623" name="__module.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="624" name="Constant_37782" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="136305590" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="625" name="__module.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="484,input.69">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="626" name="self.model.decoder.layers.2.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1280" offset="136310710" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="627" name="Convert_1065519" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="628" name="self.model.decoder.layers.2.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1" offset="142864310" size="5120" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="629" name="Convert_1065522" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="630" name="self.model.decoder.layers.2.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="631" name="self.model.decoder.layers.2.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 1" offset="142869430" size="10240" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="632" name="self.model.decoder.layers.2.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="633" name="self.model.decoder.layers.2.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="634" name="__module.model.decoder.layers.2.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="635" name="Constant_37783" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="142879670" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="636" name="__module.model.decoder.layers.2.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="487,input.71">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="637" name="__module.model.decoder.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="488,input.73">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="638" name="self.model.decoder.layers.2.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 5120" offset="142900150" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="639" name="Convert_1070586" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="640" name="self.model.decoder.layers.2.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="149453750" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="641" name="Convert_1070589" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="642" name="self.model.decoder.layers.2.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="643" name="self.model.decoder.layers.2.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="149455030" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="644" name="self.model.decoder.layers.2.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="645" name="self.model.decoder.layers.2.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="646" name="__module.model.decoder.layers.2.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="647" name="Constant_37784" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="149457590" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="648" name="__module.model.decoder.layers.2.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="492,input.77">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="649" name="__module.model.decoder.layers.2/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="494,input.79">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="650" name="__module.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="651" name="__module.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="652" name="Constant_37785" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="149462710" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="653" name="__module.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="654" name="Constant_37786" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="149467830" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="655" name="__module.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="509,hidden_states.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="656" name="self.model.decoder.layers.3.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="149472950" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="657" name="Convert_1217529" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="658" name="self.model.decoder.layers.3.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="151111350" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="659" name="Convert_1217532" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="660" name="self.model.decoder.layers.3.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="661" name="self.model.decoder.layers.3.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="151112630" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="662" name="self.model.decoder.layers.3.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="663" name="self.model.decoder.layers.3.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="664" name="__module.model.decoder.layers.3.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="665" name="Constant_37787" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="151115190" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="666" name="__module.model.decoder.layers.3.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="530">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="667" name="Constant_38551" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="668" name="__module.model.decoder.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="532,value_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="669" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="670" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="535">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="671" name="__module.model.decoder.layers.3.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="present.3.decoder.value,value.13">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="672" name="ReadValue_39893" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.3.decoder.keypresent.3.decoder.key" variable_type="f32" variable_shape="?,20,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.3.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="673" name="Constant_39608" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="13158452" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="674" name="Gather_39609" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="675" name="self.model.decoder.layers.3.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="151120310" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="676" name="Convert_1222596" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="677" name="self.model.decoder.layers.3.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="152758710" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="678" name="Convert_1222599" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="679" name="self.model.decoder.layers.3.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="680" name="self.model.decoder.layers.3.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="152759990" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="681" name="self.model.decoder.layers.3.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="682" name="self.model.decoder.layers.3.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="683" name="__module.model.decoder.layers.3.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="525">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="684" name="Constant_38552" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="685" name="__module.model.decoder.layers.3.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="527,key_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="686" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="687" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="533">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="688" name="__module.model.decoder.layers.3.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.13">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="689" name="self.model.decoder.layers.3.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="152762550" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="690" name="Convert_1227663" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="691" name="self.model.decoder.layers.3.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="154400950" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="692" name="Convert_1227666" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="693" name="self.model.decoder.layers.3.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="694" name="self.model.decoder.layers.3.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="154402230" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="695" name="self.model.decoder.layers.3.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="696" name="self.model.decoder.layers.3.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="697" name="__module.model.decoder.layers.3.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="698" name="Constant_37788" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="699" name="Multiply_37524" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="700" name="Constant_37789" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="154404790" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="701" name="__module.model.decoder.layers.3.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="519,query_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="702" name="Constant_38553" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="703" name="__module.model.decoder.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="521,query_states.27">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="704" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="705" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="522">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="706" name="__module.model.decoder.layers.3.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="546,attn_output.25">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="707" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="708" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="547">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="709" name="Constant_38554" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="710" name="__module.model.decoder.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="550">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="711" name="self.model.decoder.layers.3.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="154409910" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="712" name="Convert_1232730" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="713" name="self.model.decoder.layers.3.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="156048310" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="714" name="Convert_1232733" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="715" name="self.model.decoder.layers.3.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="716" name="self.model.decoder.layers.3.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="156049590" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="717" name="self.model.decoder.layers.3.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="718" name="self.model.decoder.layers.3.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="719" name="__module.model.decoder.layers.3.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="720" name="Constant_37790" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="156052150" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="721" name="__module.model.decoder.layers.3.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="554,input.83">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="722" name="__module.model.decoder.layers.3/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="560,input.85">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="723" name="__module.model.decoder.layers.3.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="724" name="__module.model.decoder.layers.3.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="725" name="Constant_37791" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="156057270" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="726" name="__module.model.decoder.layers.3.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="727" name="Constant_37792" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="156062390" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="728" name="__module.model.decoder.layers.3.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="564,hidden_states.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="729" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="156067510" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="730" name="Convert_1237797" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="731" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="157705910" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="732" name="Convert_1237800" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="733" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="734" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="157707190" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="735" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="736" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="737" name="__module.model.decoder.layers.3.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="738" name="Constant_37793" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="81929858" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="739" name="Multiply_37528" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="740" name="Constant_37794" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="157709750" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="741" name="__module.model.decoder.layers.3.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="574,query_states.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="742" name="Constant_38555" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="1642240" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="743" name="__module.model.decoder.layers.3.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="576,query_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="744" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="745" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="577">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="746" name="__module.model.decoder.layers.3.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="13158448" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="747" name="__module.model.decoder.layers.3.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="592,attn_output.29">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="748" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="1642272" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="749" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="593">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="750" name="Constant_38558" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="85224606" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="751" name="__module.model.decoder.layers.3.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="596">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="752" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1280" offset="157714870" size="1638400" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="753" name="Convert_1242864" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="754" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="159353270" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="755" name="Convert_1242867" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="756" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="757" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="159354550" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="758" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="759" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="760" name="__module.model.decoder.layers.3.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="761" name="Constant_37796" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="159357110" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="762" name="__module.model.decoder.layers.3.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="600,input.89">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="763" name="__module.model.decoder.layers.3/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="602,input.91">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="764" name="__module.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="765" name="__module.model.decoder.layers.3.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="766" name="Constant_37797" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="159362230" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="767" name="__module.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="768" name="Constant_37798" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="159367350" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="769" name="__module.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="606,input.93">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="770" name="self.model.decoder.layers.3.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1280" offset="159372470" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="771" name="Convert_1075653" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="772" name="self.model.decoder.layers.3.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="5120, 1" offset="165926070" size="5120" />
			<output>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="773" name="Convert_1075656" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="774" name="self.model.decoder.layers.3.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="775" name="self.model.decoder.layers.3.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 1" offset="165931190" size="10240" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="776" name="self.model.decoder.layers.3.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="777" name="self.model.decoder.layers.3.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="778" name="__module.model.decoder.layers.3.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="779" name="Constant_37799" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="165941430" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="780" name="__module.model.decoder.layers.3.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="609,input.95">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="781" name="__module.model.decoder.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="610,input.97">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="782" name="self.model.decoder.layers.3.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 5120" offset="165961910" size="6553600" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="783" name="Convert_1080720" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="784" name="self.model.decoder.layers.3.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="1280, 1" offset="172515510" size="1280" />
			<output>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="785" name="Convert_1080723" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="786" name="self.model.decoder.layers.3.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="787" name="self.model.decoder.layers.3.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="172516790" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="788" name="self.model.decoder.layers.3.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="789" name="self.model.decoder.layers.3.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="790" name="__module.model.decoder.layers.3.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="791" name="Constant_37800" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="172519350" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="792" name="__module.model.decoder.layers.3.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="614,input.101">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="793" name="__module.model.decoder.layers.3/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="616,input.103">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="794" name="__module.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="80277374" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="795" name="__module.model.decoder.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="796" name="Constant_37801" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="172524470" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="797" name="__module.model.decoder.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="798" name="Constant_37802" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="172529590" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="799" name="__module.model.decoder.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="624,input">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="800" name="__module.proj_out/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="logits">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51866</dim>
				</port>
			</output>
		</layer>
		<layer id="801" name="Assign_39882" type="Assign" version="opset6">
			<data variable_id="past_key_values.0.decoder.keypresent.0.decoder.key" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="802" name="Assign_39884" type="Assign" version="opset6">
			<data variable_id="past_key_values.0.decoder.valuepresent.0.decoder.value" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="803" name="Assign_39886" type="Assign" version="opset6">
			<data variable_id="past_key_values.1.decoder.keypresent.1.decoder.key" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="804" name="Assign_39888" type="Assign" version="opset6">
			<data variable_id="past_key_values.1.decoder.valuepresent.1.decoder.value" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="805" name="Assign_39890" type="Assign" version="opset6">
			<data variable_id="past_key_values.2.decoder.keypresent.2.decoder.key" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="806" name="Assign_39892" type="Assign" version="opset6">
			<data variable_id="past_key_values.2.decoder.valuepresent.2.decoder.value" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="807" name="Assign_39894" type="Assign" version="opset6">
			<data variable_id="past_key_values.3.decoder.keypresent.3.decoder.key" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="808" name="Assign_39896" type="Assign" version="opset6">
			<data variable_id="past_key_values.3.decoder.valuepresent.3.decoder.value" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="809" name="Assign_40552" type="Assign" version="opset6">
			<data variable_id="588" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="810" name="Assign_40554" type="Assign" version="opset6">
			<data variable_id="468" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="811" name="Assign_40556" type="Assign" version="opset6">
			<data variable_id="224" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="812" name="Assign_40558" type="Assign" version="opset6">
			<data variable_id="222" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="813" name="Assign_40560" type="Assign" version="opset6">
			<data variable_id="344" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="814" name="Assign_40562" type="Assign" version="opset6">
			<data variable_id="590" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="815" name="Assign_40564" type="Assign" version="opset6">
			<data variable_id="346" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="816" name="Assign_40566" type="Assign" version="opset6">
			<data variable_id="466" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="817" name="Result_27845" type="Result" version="opset1" output_names="logits">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51866</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="145" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="124" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="11" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="117" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="41" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="101" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="57" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="71" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="25" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="85" to-port="0" />
		<edge from-layer="2" from-port="0" to-layer="381" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="674" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="545" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="528" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="398" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="159" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="135" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="218" to-port="1" />
		<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
		<edge from-layer="4" from-port="1" to-layer="7" to-port="0" />
		<edge from-layer="5" from-port="0" to-layer="6" to-port="0" />
		<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
		<edge from-layer="7" from-port="2" to-layer="9" to-port="0" />
		<edge from-layer="8" from-port="0" to-layer="9" to-port="1" />
		<edge from-layer="9" from-port="2" to-layer="10" to-port="0" />
		<edge from-layer="10" from-port="1" to-layer="11" to-port="1" />
		<edge from-layer="11" from-port="2" to-layer="13" to-port="0" />
		<edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
		<edge from-layer="13" from-port="2" to-layer="15" to-port="0" />
		<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
		<edge from-layer="15" from-port="2" to-layer="16" to-port="0" />
		<edge from-layer="16" from-port="1" to-layer="816" to-port="0" />
		<edge from-layer="16" from-port="1" to-layer="603" to-port="1" />
		<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
		<edge from-layer="18" from-port="1" to-layer="21" to-port="0" />
		<edge from-layer="19" from-port="0" 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="25" to-port="1" />
		<edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
		<edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
		<edge from-layer="27" from-port="2" to-layer="29" to-port="0" />
		<edge from-layer="28" from-port="0" to-layer="29" to-port="1" />
		<edge from-layer="29" from-port="2" to-layer="31" to-port="0" />
		<edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
		<edge from-layer="31" from-port="2" to-layer="32" to-port="0" />
		<edge from-layer="32" from-port="1" to-layer="815" to-port="0" />
		<edge from-layer="32" from-port="1" to-layer="456" to-port="2" />
		<edge from-layer="33" from-port="0" to-layer="34" to-port="0" />
		<edge from-layer="34" from-port="1" to-layer="37" 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="37" to-port="1" />
		<edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
		<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
		<edge from-layer="39" from-port="2" to-layer="40" to-port="0" />
		<edge from-layer="40" from-port="1" to-layer="41" to-port="1" />
		<edge from-layer="41" from-port="2" to-layer="43" to-port="0" />
		<edge from-layer="42" from-port="0" 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="48" to-port="0" />
		<edge from-layer="48" from-port="1" to-layer="814" to-port="0" />
		<edge from-layer="48" from-port="1" to-layer="747" to-port="2" />
		<edge from-layer="49" from-port="0" to-layer="50" to-port="0" />
		<edge from-layer="50" from-port="1" to-layer="53" to-port="0" />
		<edge from-layer="51" from-port="0" to-layer="52" to-port="0" />
		<edge from-layer="52" from-port="1" to-layer="53" to-port="1" />
		<edge from-layer="53" from-port="2" to-layer="55" to-port="0" />
		<edge from-layer="54" from-port="0" to-layer="55" to-port="1" />
		<edge from-layer="55" from-port="2" to-layer="56" to-port="0" />
		<edge from-layer="56" from-port="1" to-layer="57" to-port="1" />
		<edge from-layer="57" from-port="2" to-layer="59" to-port="0" />
		<edge from-layer="58" from-port="0" to-layer="59" to-port="1" />
		<edge from-layer="59" from-port="2" to-layer="61" to-port="0" />
		<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
		<edge from-layer="61" from-port="2" to-layer="62" to-port="0" />
		<edge from-layer="62" from-port="1" to-layer="813" to-port="0" />
		<edge from-layer="62" from-port="1" to-layer="456" to-port="1" />
		<edge from-layer="63" from-port="0" to-layer="64" to-port="0" />
		<edge from-layer="64" from-port="1" to-layer="67" to-port="0" />
		<edge from-layer="65" from-port="0" to-layer="66" to-port="0" />
		<edge from-layer="66" from-port="1" to-layer="67" to-port="1" />
		<edge from-layer="67" from-port="2" to-layer="69" to-port="0" />
		<edge from-layer="68" from-port="0" to-layer="69" to-port="1" />
		<edge from-layer="69" from-port="2" to-layer="70" to-port="0" />
		<edge from-layer="70" from-port="1" to-layer="71" to-port="1" />
		<edge from-layer="71" from-port="2" to-layer="73" to-port="0" />
		<edge from-layer="72" from-port="0" 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="76" to-port="0" />
		<edge from-layer="76" from-port="1" to-layer="309" to-port="1" />
		<edge from-layer="76" from-port="1" to-layer="812" to-port="0" />
		<edge from-layer="77" from-port="0" to-layer="78" to-port="0" />
		<edge from-layer="78" from-port="1" to-layer="81" to-port="0" />
		<edge from-layer="79" from-port="0" to-layer="80" to-port="0" />
		<edge from-layer="80" from-port="1" to-layer="81" to-port="1" />
		<edge from-layer="81" from-port="2" to-layer="83" to-port="0" />
		<edge from-layer="82" from-port="0" to-layer="83" to-port="1" />
		<edge from-layer="83" from-port="2" to-layer="84" to-port="0" />
		<edge from-layer="84" from-port="1" to-layer="85" to-port="1" />
		<edge from-layer="85" from-port="2" to-layer="87" to-port="0" />
		<edge from-layer="86" from-port="0" to-layer="87" to-port="1" />
		<edge from-layer="87" from-port="2" to-layer="89" to-port="0" />
		<edge from-layer="88" from-port="0" 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="811" to-port="0" />
		<edge from-layer="92" from-port="1" to-layer="309" to-port="2" />
		<edge from-layer="93" from-port="0" to-layer="94" to-port="0" />
		<edge from-layer="94" from-port="1" to-layer="97" to-port="0" />
		<edge from-layer="95" from-port="0" to-layer="96" to-port="0" />
		<edge from-layer="96" from-port="1" to-layer="97" to-port="1" />
		<edge from-layer="97" from-port="2" to-layer="99" to-port="0" />
		<edge from-layer="98" from-port="0" to-layer="99" to-port="1" />
		<edge from-layer="99" from-port="2" to-layer="100" to-port="0" />
		<edge from-layer="100" from-port="1" to-layer="101" to-port="1" />
		<edge from-layer="101" from-port="2" to-layer="103" to-port="0" />
		<edge from-layer="102" from-port="0" to-layer="103" to-port="1" />
		<edge from-layer="103" from-port="2" to-layer="105" to-port="0" />
		<edge from-layer="104" from-port="0" to-layer="105" to-port="1" />
		<edge from-layer="105" from-port="2" to-layer="107" to-port="0" />
		<edge from-layer="106" from-port="0" to-layer="107" to-port="1" />
		<edge from-layer="107" from-port="2" to-layer="108" to-port="0" />
		<edge from-layer="108" from-port="1" to-layer="603" to-port="2" />
		<edge from-layer="108" from-port="1" to-layer="810" to-port="0" />
		<edge from-layer="109" from-port="0" to-layer="110" to-port="0" />
		<edge from-layer="110" from-port="1" to-layer="113" to-port="0" />
		<edge from-layer="111" from-port="0" to-layer="112" to-port="0" />
		<edge from-layer="112" from-port="1" to-layer="113" to-port="1" />
		<edge from-layer="113" from-port="2" to-layer="115" to-port="0" />
		<edge from-layer="114" from-port="0" to-layer="115" to-port="1" />
		<edge from-layer="115" from-port="2" to-layer="116" to-port="0" />
		<edge from-layer="116" from-port="1" to-layer="117" to-port="1" />
		<edge from-layer="117" from-port="2" to-layer="119" to-port="0" />
		<edge from-layer="118" from-port="0" to-layer="119" to-port="1" />
		<edge from-layer="119" from-port="2" to-layer="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="747" to-port="1" />
		<edge from-layer="122" from-port="1" to-layer="809" to-port="0" />
		<edge from-layer="123" from-port="0" to-layer="132" to-port="0" />
		<edge from-layer="124" from-port="1" to-layer="127" to-port="0" />
		<edge from-layer="124" from-port="1" to-layer="166" to-port="0" />
		<edge from-layer="125" from-port="0" to-layer="127" to-port="1" />
		<edge from-layer="126" from-port="0" to-layer="127" to-port="2" />
		<edge from-layer="127" from-port="3" to-layer="131" to-port="0" />
		<edge from-layer="127" from-port="3" to-layer="173" to-port="0" />
		<edge from-layer="127" from-port="3" to-layer="255" to-port="0" />
		<edge from-layer="128" from-port="0" to-layer="131" to-port="1" />
		<edge from-layer="129" from-port="0" to-layer="131" to-port="2" />
		<edge from-layer="130" from-port="0" to-layer="131" to-port="3" />
		<edge from-layer="131" from-port="4" to-layer="132" to-port="1" />
		<edge from-layer="132" from-port="2" to-layer="396" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="526" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="543" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="216" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="672" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="157" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="133" to-port="0" />
		<edge from-layer="132" from-port="2" to-layer="379" to-port="0" />
		<edge from-layer="133" from-port="1" to-layer="135" to-port="0" />
		<edge from-layer="134" from-port="0" to-layer="135" to-port="2" />
		<edge from-layer="135" from-port="3" to-layer="671" to-port="0" />
		<edge from-layer="136" from-port="0" to-layer="137" to-port="0" />
		<edge from-layer="137" from-port="1" to-layer="140" to-port="0" />
		<edge from-layer="138" from-port="0" to-layer="139" to-port="0" />
		<edge from-layer="139" from-port="1" to-layer="140" to-port="1" />
		<edge from-layer="140" from-port="2" to-layer="142" to-port="0" />
		<edge from-layer="141" from-port="0" to-layer="142" to-port="1" />
		<edge from-layer="142" from-port="2" to-layer="143" to-port="0" />
		<edge from-layer="143" from-port="1" to-layer="800" to-port="1" />
		<edge from-layer="143" from-port="1" to-layer="148" 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="146" to-port="0" />
		<edge from-layer="146" from-port="1" to-layer="148" to-port="1" />
		<edge from-layer="147" from-port="0" to-layer="148" to-port="2" />
		<edge from-layer="148" from-port="3" to-layer="178" to-port="0" />
		<edge from-layer="149" from-port="0" to-layer="150" to-port="0" />
		<edge from-layer="150" from-port="1" to-layer="153" to-port="0" />
		<edge from-layer="151" from-port="0" to-layer="152" to-port="0" />
		<edge from-layer="152" from-port="1" to-layer="153" to-port="1" />
		<edge from-layer="153" from-port="2" to-layer="155" to-port="0" />
		<edge from-layer="154" from-port="0" to-layer="155" to-port="1" />
		<edge from-layer="155" from-port="2" to-layer="156" to-port="0" />
		<edge from-layer="156" from-port="1" to-layer="177" to-port="0" />
		<edge from-layer="157" from-port="1" to-layer="159" to-port="0" />
		<edge from-layer="158" from-port="0" to-layer="159" to-port="2" />
		<edge from-layer="159" from-port="3" to-layer="160" to-port="0" />
		<edge from-layer="159" from-port="3" to-layer="215" to-port="0" />
		<edge from-layer="160" from-port="1" to-layer="163" to-port="0" />
		<edge from-layer="161" from-port="0" to-layer="163" to-port="1" />
		<edge from-layer="162" from-port="0" to-layer="163" to-port="2" />
		<edge from-layer="163" from-port="3" to-layer="240" to-port="0" />
		<edge from-layer="163" from-port="3" to-layer="169" to-port="0" />
		<edge from-layer="163" from-port="3" to-layer="262" to-port="0" />
		<edge from-layer="163" from-port="3" to-layer="167" to-port="0" />
		<edge from-layer="164" from-port="0" to-layer="166" to-port="1" />
		<edge from-layer="165" from-port="0" to-layer="166" to-port="2" />
		<edge from-layer="166" from-port="3" to-layer="167" to-port="1" />
		<edge from-layer="166" from-port="3" to-layer="237" to-port="0" />
		<edge from-layer="167" from-port="2" to-layer="169" to-port="1" />
		<edge from-layer="168" from-port="0" to-layer="169" to-port="2" />
		<edge from-layer="169" from-port="3" to-layer="171" to-port="0" />
		<edge from-layer="170" from-port="0" to-layer="171" to-port="1" />
		<edge from-layer="170" from-port="0" to-layer="243" to-port="1" />
		<edge from-layer="171" from-port="2" to-layer="174" to-port="0" />
		<edge from-layer="171" from-port="2" to-layer="248" 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="174" to-port="1" />
		<edge from-layer="174" from-port="2" to-layer="175" to-port="0" />
		<edge from-layer="175" from-port="1" to-layer="177" to-port="1" />
		<edge from-layer="176" from-port="0" to-layer="177" to-port="2" />
		<edge from-layer="177" from-port="3" to-layer="178" to-port="1" />
		<edge from-layer="178" from-port="2" to-layer="180" to-port="0" />
		<edge from-layer="178" from-port="2" to-layer="284" 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="184" to-port="0" />
		<edge from-layer="183" from-port="0" to-layer="184" to-port="1" />
		<edge from-layer="184" from-port="2" to-layer="210" to-port="0" />
		<edge from-layer="184" from-port="2" to-layer="227" to-port="0" />
		<edge from-layer="184" from-port="2" to-layer="193" 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="189" to-port="0" />
		<edge from-layer="187" from-port="0" to-layer="188" to-port="0" />
		<edge from-layer="188" from-port="1" to-layer="189" to-port="1" />
		<edge from-layer="189" from-port="2" to-layer="191" to-port="0" />
		<edge from-layer="190" from-port="0" to-layer="191" to-port="1" />
		<edge from-layer="191" from-port="2" to-layer="192" to-port="0" />
		<edge from-layer="192" from-port="1" to-layer="193" to-port="1" />
		<edge from-layer="193" from-port="2" to-layer="195" to-port="0" />
		<edge from-layer="194" from-port="0" to-layer="195" to-port="1" />
		<edge from-layer="195" from-port="2" to-layer="197" to-port="0" />
		<edge from-layer="196" from-port="0" to-layer="197" to-port="1" />
		<edge from-layer="197" from-port="2" to-layer="199" to-port="0" />
		<edge from-layer="198" from-port="0" to-layer="199" to-port="1" />
		<edge from-layer="199" from-port="2" to-layer="201" to-port="0" />
		<edge from-layer="200" from-port="0" to-layer="201" to-port="1" />
		<edge from-layer="201" from-port="2" to-layer="268" to-port="0" />
		<edge from-layer="202" from-port="0" to-layer="203" to-port="0" />
		<edge from-layer="203" from-port="1" to-layer="206" to-port="0" />
		<edge from-layer="204" from-port="0" to-layer="205" to-port="0" />
		<edge from-layer="205" from-port="1" to-layer="206" to-port="1" />
		<edge from-layer="206" from-port="2" to-layer="208" to-port="0" />
		<edge from-layer="207" from-port="0" to-layer="208" to-port="1" />
		<edge from-layer="208" from-port="2" to-layer="209" to-port="0" />
		<edge from-layer="209" from-port="1" to-layer="210" to-port="1" />
		<edge from-layer="210" from-port="2" to-layer="212" to-port="0" />
		<edge from-layer="211" from-port="0" to-layer="212" to-port="1" />
		<edge from-layer="212" from-port="2" to-layer="214" to-port="0" />
		<edge from-layer="213" from-port="0" to-layer="214" to-port="1" />
		<edge from-layer="214" from-port="2" to-layer="215" to-port="1" />
		<edge from-layer="215" from-port="2" to-layer="801" to-port="0" />
		<edge from-layer="215" from-port="2" to-layer="268" to-port="1" />
		<edge from-layer="216" from-port="1" to-layer="218" to-port="0" />
		<edge from-layer="217" from-port="0" to-layer="218" to-port="2" />
		<edge from-layer="218" from-port="3" to-layer="234" to-port="0" />
		<edge from-layer="219" from-port="0" to-layer="220" to-port="0" />
		<edge from-layer="220" from-port="1" to-layer="223" to-port="0" />
		<edge from-layer="221" from-port="0" to-layer="222" to-port="0" />
		<edge from-layer="222" from-port="1" to-layer="223" to-port="1" />
		<edge from-layer="223" from-port="2" to-layer="225" to-port="0" />
		<edge from-layer="224" from-port="0" to-layer="225" to-port="1" />
		<edge from-layer="225" from-port="2" to-layer="226" to-port="0" />
		<edge from-layer="226" from-port="1" to-layer="227" to-port="1" />
		<edge from-layer="227" from-port="2" to-layer="229" to-port="0" />
		<edge from-layer="228" from-port="0" to-layer="229" to-port="1" />
		<edge from-layer="229" from-port="2" to-layer="231" to-port="0" />
		<edge from-layer="230" from-port="0" to-layer="231" to-port="1" />
		<edge from-layer="231" from-port="2" to-layer="233" to-port="0" />
		<edge from-layer="232" from-port="0" to-layer="233" to-port="1" />
		<edge from-layer="233" from-port="2" to-layer="234" to-port="1" />
		<edge from-layer="234" from-port="2" to-layer="268" to-port="2" />
		<edge from-layer="234" from-port="2" to-layer="802" to-port="0" />
		<edge from-layer="235" from-port="0" to-layer="242" 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="255" to-port="2" />
		<edge from-layer="237" from-port="2" to-layer="263" to-port="1" />
		<edge from-layer="237" from-port="2" to-layer="239" to-port="0" />
		<edge from-layer="238" from-port="0" to-layer="239" to-port="1" />
		<edge from-layer="239" from-port="2" to-layer="240" to-port="1" />
		<edge from-layer="240" from-port="2" to-layer="254" to-port="0" />
		<edge from-layer="240" from-port="2" to-layer="242" to-port="1" />
		<edge from-layer="241" from-port="0" to-layer="242" to-port="2" />
		<edge from-layer="242" from-port="3" to-layer="243" to-port="0" />
		<edge from-layer="243" from-port="2" to-layer="245" to-port="0" />
		<edge from-layer="244" from-port="0" to-layer="248" to-port="1" />
		<edge from-layer="244" from-port="0" to-layer="245" to-port="1" />
		<edge from-layer="245" from-port="2" to-layer="247" to-port="0" />
		<edge from-layer="246" from-port="0" to-layer="247" to-port="1" />
		<edge from-layer="247" from-port="2" to-layer="251" to-port="0" />
		<edge from-layer="248" from-port="2" to-layer="250" to-port="0" />
		<edge from-layer="249" from-port="0" to-layer="250" to-port="1" />
		<edge from-layer="250" from-port="2" to-layer="251" to-port="1" />
		<edge from-layer="251" from-port="2" to-layer="256" to-port="0" />
		<edge from-layer="252" from-port="0" to-layer="255" to-port="1" />
		<edge from-layer="253" from-port="0" to-layer="254" to-port="1" />
		<edge from-layer="254" from-port="2" to-layer="255" to-port="3" />
		<edge from-layer="255" from-port="4" to-layer="256" to-port="1" />
		<edge from-layer="256" from-port="2" to-layer="259" to-port="0" />
		<edge from-layer="257" from-port="0" to-layer="259" to-port="1" />
		<edge from-layer="258" from-port="0" to-layer="259" to-port="2" />
		<edge from-layer="259" from-port="3" to-layer="266" to-port="0" />
		<edge from-layer="260" from-port="0" to-layer="266" to-port="1" />
		<edge from-layer="261" from-port="0" to-layer="262" to-port="1" />
		<edge from-layer="262" from-port="2" to-layer="263" to-port="0" />
		<edge from-layer="263" from-port="2" to-layer="266" to-port="2" />
		<edge from-layer="264" from-port="0" to-layer="266" to-port="3" />
		<edge from-layer="265" from-port="0" to-layer="266" to-port="4" />
		<edge from-layer="266" from-port="5" to-layer="268" to-port="3" />
		<edge from-layer="266" from-port="5" to-layer="415" to-port="3" />
		<edge from-layer="266" from-port="5" to-layer="706" to-port="3" />
		<edge from-layer="266" from-port="5" to-layer="562" to-port="3" />
		<edge from-layer="267" from-port="0" to-layer="268" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="603" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="706" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="309" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="415" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="456" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="562" to-port="4" />
		<edge from-layer="267" from-port="0" to-layer="747" to-port="4" />
		<edge from-layer="268" from-port="5" to-layer="270" to-port="0" />
		<edge from-layer="269" from-port="0" to-layer="270" to-port="1" />
		<edge from-layer="270" from-port="2" to-layer="272" to-port="0" />
		<edge from-layer="271" from-port="0" to-layer="272" to-port="1" />
		<edge from-layer="272" from-port="2" to-layer="281" to-port="0" />
		<edge from-layer="273" from-port="0" to-layer="274" to-port="0" />
		<edge from-layer="274" from-port="1" to-layer="277" to-port="0" />
		<edge from-layer="275" from-port="0" to-layer="276" to-port="0" />
		<edge from-layer="276" from-port="1" to-layer="277" to-port="1" />
		<edge from-layer="277" from-port="2" to-layer="279" to-port="0" />
		<edge from-layer="278" from-port="0" to-layer="279" to-port="1" />
		<edge from-layer="279" from-port="2" to-layer="280" to-port="0" />
		<edge from-layer="280" from-port="1" to-layer="281" to-port="1" />
		<edge from-layer="281" from-port="2" to-layer="283" to-port="0" />
		<edge from-layer="282" from-port="0" to-layer="283" to-port="1" />
		<edge from-layer="283" from-port="2" to-layer="284" to-port="1" />
		<edge from-layer="284" from-port="2" to-layer="286" to-port="0" />
		<edge from-layer="284" from-port="2" to-layer="325" to-port="0" />
		<edge from-layer="285" from-port="0" to-layer="286" to-port="1" />
		<edge from-layer="286" from-port="2" to-layer="288" to-port="0" />
		<edge from-layer="287" from-port="0" to-layer="288" to-port="1" />
		<edge from-layer="288" from-port="2" to-layer="290" to-port="0" />
		<edge from-layer="289" from-port="0" to-layer="290" to-port="1" />
		<edge from-layer="290" from-port="2" to-layer="299" to-port="0" />
		<edge from-layer="291" from-port="0" to-layer="292" to-port="0" />
		<edge from-layer="292" from-port="1" to-layer="295" to-port="0" />
		<edge from-layer="293" from-port="0" to-layer="294" to-port="0" />
		<edge from-layer="294" from-port="1" to-layer="295" to-port="1" />
		<edge from-layer="295" from-port="2" to-layer="297" to-port="0" />
		<edge from-layer="296" from-port="0" to-layer="297" to-port="1" />
		<edge from-layer="297" from-port="2" to-layer="298" to-port="0" />
		<edge from-layer="298" from-port="1" to-layer="299" to-port="1" />
		<edge from-layer="299" from-port="2" to-layer="301" to-port="0" />
		<edge from-layer="300" from-port="0" to-layer="301" to-port="1" />
		<edge from-layer="301" from-port="2" to-layer="303" to-port="0" />
		<edge from-layer="302" from-port="0" to-layer="303" to-port="1" />
		<edge from-layer="303" from-port="2" to-layer="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="307" to-port="0" />
		<edge from-layer="306" from-port="0" to-layer="307" to-port="1" />
		<edge from-layer="307" from-port="2" to-layer="309" to-port="0" />
		<edge from-layer="308" from-port="0" to-layer="309" to-port="3" />
		<edge from-layer="309" from-port="5" to-layer="311" to-port="0" />
		<edge from-layer="310" from-port="0" to-layer="311" to-port="1" />
		<edge from-layer="311" from-port="2" to-layer="313" to-port="0" />
		<edge from-layer="312" from-port="0" to-layer="313" to-port="1" />
		<edge from-layer="313" from-port="2" to-layer="322" to-port="0" />
		<edge from-layer="314" from-port="0" to-layer="315" to-port="0" />
		<edge from-layer="315" from-port="1" to-layer="318" to-port="0" />
		<edge from-layer="316" from-port="0" to-layer="317" to-port="0" />
		<edge from-layer="317" from-port="1" to-layer="318" to-port="1" />
		<edge from-layer="318" from-port="2" to-layer="320" to-port="0" />
		<edge from-layer="319" from-port="0" to-layer="320" to-port="1" />
		<edge from-layer="320" from-port="2" to-layer="321" to-port="0" />
		<edge from-layer="321" from-port="1" to-layer="322" to-port="1" />
		<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="325" to-port="1" />
		<edge from-layer="325" from-port="2" to-layer="355" to-port="0" />
		<edge from-layer="325" from-port="2" to-layer="327" to-port="0" />
		<edge from-layer="326" from-port="0" to-layer="327" to-port="1" />
		<edge from-layer="327" from-port="2" to-layer="329" to-port="0" />
		<edge from-layer="328" from-port="0" to-layer="329" to-port="1" />
		<edge from-layer="329" from-port="2" to-layer="331" to-port="0" />
		<edge from-layer="330" from-port="0" to-layer="331" to-port="1" />
		<edge from-layer="331" from-port="2" to-layer="340" to-port="0" />
		<edge from-layer="332" from-port="0" to-layer="333" to-port="0" />
		<edge from-layer="333" from-port="1" to-layer="336" to-port="0" />
		<edge from-layer="334" from-port="0" to-layer="335" to-port="0" />
		<edge from-layer="335" from-port="1" to-layer="336" to-port="1" />
		<edge from-layer="336" from-port="2" to-layer="338" to-port="0" />
		<edge from-layer="337" from-port="0" to-layer="338" to-port="1" />
		<edge from-layer="338" from-port="2" to-layer="339" to-port="0" />
		<edge from-layer="339" from-port="1" to-layer="340" to-port="1" />
		<edge from-layer="340" from-port="2" to-layer="342" to-port="0" />
		<edge from-layer="341" from-port="0" to-layer="342" to-port="1" />
		<edge from-layer="342" from-port="2" to-layer="343" to-port="0" />
		<edge from-layer="343" from-port="1" to-layer="352" 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="355" to-port="1" />
		<edge from-layer="355" from-port="2" to-layer="357" to-port="0" />
		<edge from-layer="355" from-port="2" to-layer="431" to-port="0" />
		<edge from-layer="356" from-port="0" to-layer="357" to-port="1" />
		<edge from-layer="357" from-port="2" to-layer="359" to-port="0" />
		<edge from-layer="358" from-port="0" to-layer="359" to-port="1" />
		<edge from-layer="359" from-port="2" to-layer="361" to-port="0" />
		<edge from-layer="360" from-port="0" to-layer="361" to-port="1" />
		<edge from-layer="361" from-port="2" to-layer="390" to-port="0" />
		<edge from-layer="361" from-port="2" to-layer="407" to-port="0" />
		<edge from-layer="361" from-port="2" to-layer="370" to-port="0" />
		<edge from-layer="362" from-port="0" to-layer="363" to-port="0" />
		<edge from-layer="363" from-port="1" to-layer="366" to-port="0" />
		<edge from-layer="364" from-port="0" to-layer="365" to-port="0" />
		<edge from-layer="365" from-port="1" to-layer="366" to-port="1" />
		<edge from-layer="366" from-port="2" to-layer="368" to-port="0" />
		<edge from-layer="367" from-port="0" to-layer="368" to-port="1" />
		<edge from-layer="368" from-port="2" to-layer="369" to-port="0" />
		<edge from-layer="369" from-port="1" to-layer="370" to-port="1" />
		<edge from-layer="370" from-port="2" to-layer="372" to-port="0" />
		<edge from-layer="371" from-port="0" to-layer="372" to-port="1" />
		<edge from-layer="372" from-port="2" to-layer="374" to-port="0" />
		<edge from-layer="373" from-port="0" 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="415" to-port="0" />
		<edge from-layer="379" from-port="1" to-layer="381" to-port="0" />
		<edge from-layer="380" from-port="0" to-layer="381" to-port="2" />
		<edge from-layer="381" from-port="3" to-layer="395" to-port="0" />
		<edge from-layer="382" from-port="0" to-layer="383" to-port="0" />
		<edge from-layer="383" from-port="1" to-layer="386" to-port="0" />
		<edge from-layer="384" from-port="0" to-layer="385" to-port="0" />
		<edge from-layer="385" from-port="1" to-layer="386" to-port="1" />
		<edge from-layer="386" from-port="2" to-layer="388" to-port="0" />
		<edge from-layer="387" from-port="0" to-layer="388" to-port="1" />
		<edge from-layer="388" from-port="2" to-layer="389" to-port="0" />
		<edge from-layer="389" from-port="1" to-layer="390" to-port="1" />
		<edge from-layer="390" from-port="2" to-layer="392" to-port="0" />
		<edge from-layer="391" from-port="0" to-layer="392" to-port="1" />
		<edge from-layer="392" from-port="2" to-layer="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="395" to-port="1" />
		<edge from-layer="395" from-port="2" to-layer="803" to-port="0" />
		<edge from-layer="395" from-port="2" to-layer="415" to-port="1" />
		<edge from-layer="396" from-port="1" to-layer="398" to-port="0" />
		<edge from-layer="397" from-port="0" to-layer="398" to-port="2" />
		<edge from-layer="398" from-port="3" to-layer="414" 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="403" to-port="0" />
		<edge from-layer="401" from-port="0" to-layer="402" to-port="0" />
		<edge from-layer="402" from-port="1" to-layer="403" to-port="1" />
		<edge from-layer="403" from-port="2" to-layer="405" to-port="0" />
		<edge from-layer="404" from-port="0" to-layer="405" to-port="1" />
		<edge from-layer="405" from-port="2" to-layer="406" to-port="0" />
		<edge from-layer="406" from-port="1" to-layer="407" to-port="1" />
		<edge from-layer="407" from-port="2" to-layer="409" to-port="0" />
		<edge from-layer="408" from-port="0" to-layer="409" to-port="1" />
		<edge from-layer="409" from-port="2" to-layer="411" to-port="0" />
		<edge from-layer="410" from-port="0" to-layer="411" to-port="1" />
		<edge from-layer="411" from-port="2" to-layer="413" to-port="0" />
		<edge from-layer="412" from-port="0" to-layer="413" to-port="1" />
		<edge from-layer="413" from-port="2" to-layer="414" to-port="1" />
		<edge from-layer="414" from-port="2" to-layer="804" to-port="0" />
		<edge from-layer="414" from-port="2" to-layer="415" to-port="2" />
		<edge from-layer="415" from-port="5" to-layer="417" to-port="0" />
		<edge from-layer="416" from-port="0" to-layer="417" to-port="1" />
		<edge from-layer="417" from-port="2" to-layer="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="428" to-port="0" />
		<edge from-layer="420" from-port="0" to-layer="421" to-port="0" />
		<edge from-layer="421" from-port="1" to-layer="424" to-port="0" />
		<edge from-layer="422" from-port="0" to-layer="423" to-port="0" />
		<edge from-layer="423" from-port="1" to-layer="424" to-port="1" />
		<edge from-layer="424" from-port="2" to-layer="426" to-port="0" />
		<edge from-layer="425" from-port="0" to-layer="426" to-port="1" />
		<edge from-layer="426" from-port="2" to-layer="427" to-port="0" />
		<edge from-layer="427" from-port="1" to-layer="428" to-port="1" />
		<edge from-layer="428" from-port="2" to-layer="430" to-port="0" />
		<edge from-layer="429" from-port="0" to-layer="430" to-port="1" />
		<edge from-layer="430" from-port="2" to-layer="431" to-port="1" />
		<edge from-layer="431" from-port="2" to-layer="433" to-port="0" />
		<edge from-layer="431" from-port="2" to-layer="472" to-port="0" />
		<edge from-layer="432" from-port="0" to-layer="433" to-port="1" />
		<edge from-layer="433" from-port="2" to-layer="435" to-port="0" />
		<edge from-layer="434" from-port="0" to-layer="435" to-port="1" />
		<edge from-layer="435" from-port="2" to-layer="437" to-port="0" />
		<edge from-layer="436" from-port="0" to-layer="437" to-port="1" />
		<edge from-layer="437" from-port="2" to-layer="446" to-port="0" />
		<edge from-layer="438" from-port="0" to-layer="439" to-port="0" />
		<edge from-layer="439" from-port="1" to-layer="442" to-port="0" />
		<edge from-layer="440" from-port="0" to-layer="441" to-port="0" />
		<edge from-layer="441" from-port="1" to-layer="442" to-port="1" />
		<edge from-layer="442" from-port="2" to-layer="444" to-port="0" />
		<edge from-layer="443" from-port="0" to-layer="444" to-port="1" />
		<edge from-layer="444" from-port="2" to-layer="445" to-port="0" />
		<edge from-layer="445" from-port="1" to-layer="446" to-port="1" />
		<edge from-layer="446" from-port="2" to-layer="448" to-port="0" />
		<edge from-layer="447" from-port="0" to-layer="448" to-port="1" />
		<edge from-layer="448" from-port="2" to-layer="450" to-port="0" />
		<edge from-layer="449" from-port="0" to-layer="450" to-port="1" />
		<edge from-layer="450" from-port="2" to-layer="452" to-port="0" />
		<edge from-layer="451" from-port="0" to-layer="452" to-port="1" />
		<edge from-layer="452" from-port="2" to-layer="454" to-port="0" />
		<edge from-layer="453" from-port="0" to-layer="454" to-port="1" />
		<edge from-layer="454" from-port="2" to-layer="456" to-port="0" />
		<edge from-layer="455" from-port="0" to-layer="456" to-port="3" />
		<edge from-layer="456" from-port="5" to-layer="458" to-port="0" />
		<edge from-layer="457" from-port="0" to-layer="458" to-port="1" />
		<edge from-layer="458" from-port="2" to-layer="460" to-port="0" />
		<edge from-layer="459" from-port="0" to-layer="460" to-port="1" />
		<edge from-layer="460" from-port="2" to-layer="469" to-port="0" />
		<edge from-layer="461" from-port="0" to-layer="462" to-port="0" />
		<edge from-layer="462" from-port="1" to-layer="465" to-port="0" />
		<edge from-layer="463" from-port="0" to-layer="464" to-port="0" />
		<edge from-layer="464" from-port="1" to-layer="465" to-port="1" />
		<edge from-layer="465" from-port="2" to-layer="467" to-port="0" />
		<edge from-layer="466" from-port="0" to-layer="467" to-port="1" />
		<edge from-layer="467" from-port="2" to-layer="468" to-port="0" />
		<edge from-layer="468" from-port="1" to-layer="469" to-port="1" />
		<edge from-layer="469" from-port="2" to-layer="471" to-port="0" />
		<edge from-layer="470" from-port="0" to-layer="471" to-port="1" />
		<edge from-layer="471" from-port="2" to-layer="472" to-port="1" />
		<edge from-layer="472" from-port="2" to-layer="474" to-port="0" />
		<edge from-layer="472" from-port="2" to-layer="502" to-port="0" />
		<edge from-layer="473" from-port="0" to-layer="474" to-port="1" />
		<edge from-layer="474" from-port="2" to-layer="476" to-port="0" />
		<edge from-layer="475" from-port="0" to-layer="476" to-port="1" />
		<edge from-layer="476" from-port="2" to-layer="478" to-port="0" />
		<edge from-layer="477" from-port="0" to-layer="478" to-port="1" />
		<edge from-layer="478" from-port="2" to-layer="487" to-port="0" />
		<edge from-layer="479" from-port="0" to-layer="480" to-port="0" />
		<edge from-layer="480" from-port="1" to-layer="483" to-port="0" />
		<edge from-layer="481" from-port="0" to-layer="482" to-port="0" />
		<edge from-layer="482" from-port="1" to-layer="483" to-port="1" />
		<edge from-layer="483" from-port="2" to-layer="485" to-port="0" />
		<edge from-layer="484" from-port="0" to-layer="485" to-port="1" />
		<edge from-layer="485" from-port="2" to-layer="486" to-port="0" />
		<edge from-layer="486" from-port="1" to-layer="487" to-port="1" />
		<edge from-layer="487" from-port="2" to-layer="489" to-port="0" />
		<edge from-layer="488" from-port="0" to-layer="489" to-port="1" />
		<edge from-layer="489" from-port="2" to-layer="490" to-port="0" />
		<edge from-layer="490" from-port="1" to-layer="499" to-port="0" />
		<edge from-layer="491" from-port="0" to-layer="492" to-port="0" />
		<edge from-layer="492" from-port="1" to-layer="495" to-port="0" />
		<edge from-layer="493" from-port="0" to-layer="494" to-port="0" />
		<edge from-layer="494" from-port="1" to-layer="495" to-port="1" />
		<edge from-layer="495" from-port="2" to-layer="497" to-port="0" />
		<edge from-layer="496" from-port="0" to-layer="497" to-port="1" />
		<edge from-layer="497" from-port="2" to-layer="498" to-port="0" />
		<edge from-layer="498" from-port="1" to-layer="499" to-port="1" />
		<edge from-layer="499" from-port="2" to-layer="501" to-port="0" />
		<edge from-layer="500" from-port="0" to-layer="501" to-port="1" />
		<edge from-layer="501" from-port="2" to-layer="502" to-port="1" />
		<edge from-layer="502" from-port="2" to-layer="504" to-port="0" />
		<edge from-layer="502" from-port="2" to-layer="578" to-port="0" />
		<edge from-layer="503" from-port="0" to-layer="504" to-port="1" />
		<edge from-layer="504" from-port="2" to-layer="506" to-port="0" />
		<edge from-layer="505" from-port="0" to-layer="506" to-port="1" />
		<edge from-layer="506" from-port="2" to-layer="508" to-port="0" />
		<edge from-layer="507" from-port="0" to-layer="508" to-port="1" />
		<edge from-layer="508" from-port="2" to-layer="517" to-port="0" />
		<edge from-layer="508" from-port="2" to-layer="554" to-port="0" />
		<edge from-layer="508" from-port="2" to-layer="537" to-port="0" />
		<edge from-layer="509" from-port="0" to-layer="510" to-port="0" />
		<edge from-layer="510" from-port="1" to-layer="513" to-port="0" />
		<edge from-layer="511" from-port="0" to-layer="512" to-port="0" />
		<edge from-layer="512" from-port="1" to-layer="513" to-port="1" />
		<edge from-layer="513" from-port="2" to-layer="515" to-port="0" />
		<edge from-layer="514" from-port="0" to-layer="515" to-port="1" />
		<edge from-layer="515" from-port="2" to-layer="516" to-port="0" />
		<edge from-layer="516" from-port="1" to-layer="517" to-port="1" />
		<edge from-layer="517" from-port="2" to-layer="519" to-port="0" />
		<edge from-layer="518" from-port="0" to-layer="519" to-port="1" />
		<edge from-layer="519" from-port="2" to-layer="521" to-port="0" />
		<edge from-layer="520" from-port="0" to-layer="521" to-port="1" />
		<edge from-layer="521" from-port="2" to-layer="523" to-port="0" />
		<edge from-layer="522" from-port="0" to-layer="523" to-port="1" />
		<edge from-layer="523" from-port="2" to-layer="525" to-port="0" />
		<edge from-layer="524" from-port="0" to-layer="525" to-port="1" />
		<edge from-layer="525" from-port="2" to-layer="562" to-port="0" />
		<edge from-layer="526" from-port="1" to-layer="528" to-port="0" />
		<edge from-layer="527" from-port="0" to-layer="528" to-port="2" />
		<edge from-layer="528" from-port="3" to-layer="542" to-port="0" />
		<edge from-layer="529" from-port="0" to-layer="530" to-port="0" />
		<edge from-layer="530" from-port="1" to-layer="533" to-port="0" />
		<edge from-layer="531" from-port="0" to-layer="532" to-port="0" />
		<edge from-layer="532" from-port="1" to-layer="533" to-port="1" />
		<edge from-layer="533" from-port="2" to-layer="535" to-port="0" />
		<edge from-layer="534" from-port="0" to-layer="535" to-port="1" />
		<edge from-layer="535" from-port="2" to-layer="536" to-port="0" />
		<edge from-layer="536" from-port="1" to-layer="537" to-port="1" />
		<edge from-layer="537" from-port="2" to-layer="539" to-port="0" />
		<edge from-layer="538" from-port="0" to-layer="539" to-port="1" />
		<edge from-layer="539" from-port="2" to-layer="541" to-port="0" />
		<edge from-layer="540" from-port="0" to-layer="541" to-port="1" />
		<edge from-layer="541" from-port="2" to-layer="542" to-port="1" />
		<edge from-layer="542" from-port="2" to-layer="805" to-port="0" />
		<edge from-layer="542" from-port="2" to-layer="562" to-port="1" />
		<edge from-layer="543" from-port="1" to-layer="545" to-port="0" />
		<edge from-layer="544" from-port="0" to-layer="545" to-port="2" />
		<edge from-layer="545" from-port="3" to-layer="561" to-port="0" />
		<edge from-layer="546" from-port="0" to-layer="547" to-port="0" />
		<edge from-layer="547" from-port="1" to-layer="550" to-port="0" />
		<edge from-layer="548" from-port="0" to-layer="549" to-port="0" />
		<edge from-layer="549" from-port="1" to-layer="550" to-port="1" />
		<edge from-layer="550" from-port="2" to-layer="552" to-port="0" />
		<edge from-layer="551" from-port="0" to-layer="552" to-port="1" />
		<edge from-layer="552" from-port="2" to-layer="553" to-port="0" />
		<edge from-layer="553" from-port="1" to-layer="554" to-port="1" />
		<edge from-layer="554" from-port="2" to-layer="556" to-port="0" />
		<edge from-layer="555" from-port="0" to-layer="556" to-port="1" />
		<edge from-layer="556" from-port="2" to-layer="558" to-port="0" />
		<edge from-layer="557" from-port="0" to-layer="558" to-port="1" />
		<edge from-layer="558" from-port="2" to-layer="560" to-port="0" />
		<edge from-layer="559" from-port="0" to-layer="560" to-port="1" />
		<edge from-layer="560" from-port="2" to-layer="561" to-port="1" />
		<edge from-layer="561" from-port="2" to-layer="562" to-port="2" />
		<edge from-layer="561" from-port="2" to-layer="806" to-port="0" />
		<edge from-layer="562" from-port="5" to-layer="564" to-port="0" />
		<edge from-layer="563" from-port="0" to-layer="564" to-port="1" />
		<edge from-layer="564" from-port="2" to-layer="566" to-port="0" />
		<edge from-layer="565" from-port="0" to-layer="566" to-port="1" />
		<edge from-layer="566" from-port="2" to-layer="575" to-port="0" />
		<edge from-layer="567" from-port="0" to-layer="568" to-port="0" />
		<edge from-layer="568" from-port="1" to-layer="571" to-port="0" />
		<edge from-layer="569" from-port="0" to-layer="570" to-port="0" />
		<edge from-layer="570" from-port="1" to-layer="571" to-port="1" />
		<edge from-layer="571" from-port="2" to-layer="573" to-port="0" />
		<edge from-layer="572" from-port="0" to-layer="573" to-port="1" />
		<edge from-layer="573" from-port="2" to-layer="574" to-port="0" />
		<edge from-layer="574" from-port="1" to-layer="575" to-port="1" />
		<edge from-layer="575" from-port="2" to-layer="577" to-port="0" />
		<edge from-layer="576" from-port="0" to-layer="577" to-port="1" />
		<edge from-layer="577" from-port="2" to-layer="578" to-port="1" />
		<edge from-layer="578" from-port="2" to-layer="580" to-port="0" />
		<edge from-layer="578" from-port="2" to-layer="619" to-port="0" />
		<edge from-layer="579" from-port="0" to-layer="580" to-port="1" />
		<edge from-layer="580" from-port="2" to-layer="582" to-port="0" />
		<edge from-layer="581" from-port="0" to-layer="582" to-port="1" />
		<edge from-layer="582" from-port="2" to-layer="584" to-port="0" />
		<edge from-layer="583" from-port="0" to-layer="584" to-port="1" />
		<edge from-layer="584" from-port="2" to-layer="593" to-port="0" />
		<edge from-layer="585" from-port="0" to-layer="586" to-port="0" />
		<edge from-layer="586" from-port="1" to-layer="589" to-port="0" />
		<edge from-layer="587" from-port="0" to-layer="588" to-port="0" />
		<edge from-layer="588" from-port="1" to-layer="589" to-port="1" />
		<edge from-layer="589" from-port="2" to-layer="591" to-port="0" />
		<edge from-layer="590" from-port="0" to-layer="591" to-port="1" />
		<edge from-layer="591" from-port="2" to-layer="592" to-port="0" />
		<edge from-layer="592" from-port="1" to-layer="593" to-port="1" />
		<edge from-layer="593" from-port="2" to-layer="595" to-port="0" />
		<edge from-layer="594" from-port="0" to-layer="595" to-port="1" />
		<edge from-layer="595" from-port="2" to-layer="597" to-port="0" />
		<edge from-layer="596" from-port="0" to-layer="597" to-port="1" />
		<edge from-layer="597" from-port="2" to-layer="599" to-port="0" />
		<edge from-layer="598" from-port="0" to-layer="599" to-port="1" />
		<edge from-layer="599" from-port="2" to-layer="601" to-port="0" />
		<edge from-layer="600" from-port="0" to-layer="601" to-port="1" />
		<edge from-layer="601" from-port="2" to-layer="603" to-port="0" />
		<edge from-layer="602" from-port="0" to-layer="603" to-port="3" />
		<edge from-layer="603" from-port="5" to-layer="605" to-port="0" />
		<edge from-layer="604" from-port="0" to-layer="605" to-port="1" />
		<edge from-layer="605" from-port="2" to-layer="607" to-port="0" />
		<edge from-layer="606" from-port="0" to-layer="607" to-port="1" />
		<edge from-layer="607" from-port="2" to-layer="616" to-port="0" />
		<edge from-layer="608" from-port="0" to-layer="609" to-port="0" />
		<edge from-layer="609" from-port="1" to-layer="612" to-port="0" />
		<edge from-layer="610" from-port="0" to-layer="611" to-port="0" />
		<edge from-layer="611" from-port="1" to-layer="612" to-port="1" />
		<edge from-layer="612" from-port="2" to-layer="614" to-port="0" />
		<edge from-layer="613" from-port="0" to-layer="614" to-port="1" />
		<edge from-layer="614" from-port="2" to-layer="615" to-port="0" />
		<edge from-layer="615" from-port="1" to-layer="616" to-port="1" />
		<edge from-layer="616" from-port="2" to-layer="618" to-port="0" />
		<edge from-layer="617" from-port="0" to-layer="618" to-port="1" />
		<edge from-layer="618" from-port="2" to-layer="619" to-port="1" />
		<edge from-layer="619" from-port="2" to-layer="649" to-port="0" />
		<edge from-layer="619" from-port="2" to-layer="621" to-port="0" />
		<edge from-layer="620" from-port="0" to-layer="621" to-port="1" />
		<edge from-layer="621" from-port="2" to-layer="623" to-port="0" />
		<edge from-layer="622" from-port="0" to-layer="623" to-port="1" />
		<edge from-layer="623" from-port="2" to-layer="625" to-port="0" />
		<edge from-layer="624" from-port="0" to-layer="625" to-port="1" />
		<edge from-layer="625" from-port="2" to-layer="634" to-port="0" />
		<edge from-layer="626" from-port="0" to-layer="627" to-port="0" />
		<edge from-layer="627" from-port="1" to-layer="630" to-port="0" />
		<edge from-layer="628" from-port="0" to-layer="629" to-port="0" />
		<edge from-layer="629" from-port="1" to-layer="630" to-port="1" />
		<edge from-layer="630" from-port="2" to-layer="632" to-port="0" />
		<edge from-layer="631" from-port="0" to-layer="632" to-port="1" />
		<edge from-layer="632" from-port="2" to-layer="633" to-port="0" />
		<edge from-layer="633" from-port="1" to-layer="634" to-port="1" />
		<edge from-layer="634" from-port="2" to-layer="636" to-port="0" />
		<edge from-layer="635" from-port="0" to-layer="636" to-port="1" />
		<edge from-layer="636" from-port="2" to-layer="637" to-port="0" />
		<edge from-layer="637" from-port="1" to-layer="646" to-port="0" />
		<edge from-layer="638" from-port="0" to-layer="639" to-port="0" />
		<edge from-layer="639" from-port="1" to-layer="642" to-port="0" />
		<edge from-layer="640" from-port="0" to-layer="641" to-port="0" />
		<edge from-layer="641" from-port="1" to-layer="642" to-port="1" />
		<edge from-layer="642" from-port="2" to-layer="644" to-port="0" />
		<edge from-layer="643" from-port="0" to-layer="644" to-port="1" />
		<edge from-layer="644" from-port="2" to-layer="645" to-port="0" />
		<edge from-layer="645" from-port="1" to-layer="646" to-port="1" />
		<edge from-layer="646" from-port="2" to-layer="648" to-port="0" />
		<edge from-layer="647" from-port="0" to-layer="648" to-port="1" />
		<edge from-layer="648" from-port="2" to-layer="649" to-port="1" />
		<edge from-layer="649" from-port="2" to-layer="722" to-port="0" />
		<edge from-layer="649" from-port="2" to-layer="651" to-port="0" />
		<edge from-layer="650" from-port="0" to-layer="651" to-port="1" />
		<edge from-layer="651" from-port="2" to-layer="653" to-port="0" />
		<edge from-layer="652" from-port="0" to-layer="653" to-port="1" />
		<edge from-layer="653" from-port="2" to-layer="655" to-port="0" />
		<edge from-layer="654" from-port="0" to-layer="655" to-port="1" />
		<edge from-layer="655" from-port="2" to-layer="697" to-port="0" />
		<edge from-layer="655" from-port="2" to-layer="664" to-port="0" />
		<edge from-layer="655" from-port="2" to-layer="683" to-port="0" />
		<edge from-layer="656" from-port="0" to-layer="657" to-port="0" />
		<edge from-layer="657" from-port="1" to-layer="660" to-port="0" />
		<edge from-layer="658" from-port="0" to-layer="659" to-port="0" />
		<edge from-layer="659" from-port="1" to-layer="660" to-port="1" />
		<edge from-layer="660" from-port="2" to-layer="662" to-port="0" />
		<edge from-layer="661" from-port="0" to-layer="662" to-port="1" />
		<edge from-layer="662" from-port="2" to-layer="663" to-port="0" />
		<edge from-layer="663" from-port="1" to-layer="664" to-port="1" />
		<edge from-layer="664" from-port="2" to-layer="666" to-port="0" />
		<edge from-layer="665" from-port="0" to-layer="666" to-port="1" />
		<edge from-layer="666" from-port="2" to-layer="668" to-port="0" />
		<edge from-layer="667" from-port="0" to-layer="668" to-port="1" />
		<edge from-layer="668" from-port="2" to-layer="670" to-port="0" />
		<edge from-layer="669" from-port="0" to-layer="670" to-port="1" />
		<edge from-layer="670" from-port="2" to-layer="671" to-port="1" />
		<edge from-layer="671" from-port="2" to-layer="706" to-port="2" />
		<edge from-layer="671" from-port="2" to-layer="808" to-port="0" />
		<edge from-layer="672" from-port="1" to-layer="674" to-port="0" />
		<edge from-layer="673" from-port="0" to-layer="674" to-port="2" />
		<edge from-layer="674" from-port="3" to-layer="688" to-port="0" />
		<edge from-layer="675" from-port="0" to-layer="676" to-port="0" />
		<edge from-layer="676" from-port="1" to-layer="679" to-port="0" />
		<edge from-layer="677" from-port="0" to-layer="678" to-port="0" />
		<edge from-layer="678" from-port="1" to-layer="679" to-port="1" />
		<edge from-layer="679" from-port="2" to-layer="681" to-port="0" />
		<edge from-layer="680" from-port="0" to-layer="681" to-port="1" />
		<edge from-layer="681" from-port="2" to-layer="682" to-port="0" />
		<edge from-layer="682" from-port="1" to-layer="683" to-port="1" />
		<edge from-layer="683" from-port="2" to-layer="685" to-port="0" />
		<edge from-layer="684" from-port="0" to-layer="685" to-port="1" />
		<edge from-layer="685" from-port="2" to-layer="687" to-port="0" />
		<edge from-layer="686" from-port="0" to-layer="687" to-port="1" />
		<edge from-layer="687" from-port="2" to-layer="688" to-port="1" />
		<edge from-layer="688" from-port="2" to-layer="706" to-port="1" />
		<edge from-layer="688" from-port="2" to-layer="807" to-port="0" />
		<edge from-layer="689" from-port="0" to-layer="690" to-port="0" />
		<edge from-layer="690" from-port="1" to-layer="693" to-port="0" />
		<edge from-layer="691" from-port="0" to-layer="692" to-port="0" />
		<edge from-layer="692" from-port="1" to-layer="693" to-port="1" />
		<edge from-layer="693" from-port="2" to-layer="695" to-port="0" />
		<edge from-layer="694" from-port="0" to-layer="695" to-port="1" />
		<edge from-layer="695" from-port="2" to-layer="696" to-port="0" />
		<edge from-layer="696" from-port="1" to-layer="697" to-port="1" />
		<edge from-layer="697" from-port="2" to-layer="699" to-port="0" />
		<edge from-layer="698" from-port="0" to-layer="699" to-port="1" />
		<edge from-layer="699" from-port="2" to-layer="701" to-port="0" />
		<edge from-layer="700" from-port="0" to-layer="701" to-port="1" />
		<edge from-layer="701" from-port="2" to-layer="703" to-port="0" />
		<edge from-layer="702" from-port="0" to-layer="703" to-port="1" />
		<edge from-layer="703" from-port="2" to-layer="705" to-port="0" />
		<edge from-layer="704" from-port="0" to-layer="705" to-port="1" />
		<edge from-layer="705" from-port="2" to-layer="706" to-port="0" />
		<edge from-layer="706" from-port="5" to-layer="708" to-port="0" />
		<edge from-layer="707" from-port="0" to-layer="708" to-port="1" />
		<edge from-layer="708" from-port="2" to-layer="710" to-port="0" />
		<edge from-layer="709" from-port="0" to-layer="710" to-port="1" />
		<edge from-layer="710" from-port="2" to-layer="719" to-port="0" />
		<edge from-layer="711" from-port="0" to-layer="712" to-port="0" />
		<edge from-layer="712" from-port="1" to-layer="715" to-port="0" />
		<edge from-layer="713" from-port="0" to-layer="714" to-port="0" />
		<edge from-layer="714" from-port="1" to-layer="715" to-port="1" />
		<edge from-layer="715" from-port="2" to-layer="717" to-port="0" />
		<edge from-layer="716" from-port="0" to-layer="717" to-port="1" />
		<edge from-layer="717" from-port="2" to-layer="718" to-port="0" />
		<edge from-layer="718" from-port="1" to-layer="719" to-port="1" />
		<edge from-layer="719" from-port="2" to-layer="721" to-port="0" />
		<edge from-layer="720" from-port="0" to-layer="721" to-port="1" />
		<edge from-layer="721" from-port="2" to-layer="722" to-port="1" />
		<edge from-layer="722" from-port="2" to-layer="724" to-port="0" />
		<edge from-layer="722" from-port="2" to-layer="763" to-port="0" />
		<edge from-layer="723" from-port="0" to-layer="724" to-port="1" />
		<edge from-layer="724" from-port="2" to-layer="726" to-port="0" />
		<edge from-layer="725" from-port="0" to-layer="726" to-port="1" />
		<edge from-layer="726" from-port="2" to-layer="728" to-port="0" />
		<edge from-layer="727" from-port="0" to-layer="728" to-port="1" />
		<edge from-layer="728" from-port="2" to-layer="737" to-port="0" />
		<edge from-layer="729" from-port="0" to-layer="730" to-port="0" />
		<edge from-layer="730" from-port="1" to-layer="733" to-port="0" />
		<edge from-layer="731" from-port="0" to-layer="732" to-port="0" />
		<edge from-layer="732" from-port="1" to-layer="733" to-port="1" />
		<edge from-layer="733" from-port="2" to-layer="735" to-port="0" />
		<edge from-layer="734" from-port="0" to-layer="735" to-port="1" />
		<edge from-layer="735" from-port="2" to-layer="736" to-port="0" />
		<edge from-layer="736" from-port="1" to-layer="737" to-port="1" />
		<edge from-layer="737" from-port="2" to-layer="739" to-port="0" />
		<edge from-layer="738" from-port="0" to-layer="739" to-port="1" />
		<edge from-layer="739" from-port="2" to-layer="741" to-port="0" />
		<edge from-layer="740" from-port="0" to-layer="741" to-port="1" />
		<edge from-layer="741" from-port="2" to-layer="743" to-port="0" />
		<edge from-layer="742" from-port="0" to-layer="743" to-port="1" />
		<edge from-layer="743" from-port="2" to-layer="745" to-port="0" />
		<edge from-layer="744" from-port="0" to-layer="745" to-port="1" />
		<edge from-layer="745" from-port="2" to-layer="747" to-port="0" />
		<edge from-layer="746" from-port="0" to-layer="747" to-port="3" />
		<edge from-layer="747" from-port="5" to-layer="749" to-port="0" />
		<edge from-layer="748" from-port="0" to-layer="749" to-port="1" />
		<edge from-layer="749" from-port="2" to-layer="751" to-port="0" />
		<edge from-layer="750" from-port="0" to-layer="751" to-port="1" />
		<edge from-layer="751" from-port="2" to-layer="760" to-port="0" />
		<edge from-layer="752" from-port="0" to-layer="753" to-port="0" />
		<edge from-layer="753" from-port="1" to-layer="756" to-port="0" />
		<edge from-layer="754" from-port="0" to-layer="755" to-port="0" />
		<edge from-layer="755" from-port="1" to-layer="756" to-port="1" />
		<edge from-layer="756" from-port="2" to-layer="758" to-port="0" />
		<edge from-layer="757" from-port="0" to-layer="758" to-port="1" />
		<edge from-layer="758" from-port="2" to-layer="759" to-port="0" />
		<edge from-layer="759" from-port="1" to-layer="760" to-port="1" />
		<edge from-layer="760" from-port="2" to-layer="762" to-port="0" />
		<edge from-layer="761" from-port="0" to-layer="762" to-port="1" />
		<edge from-layer="762" from-port="2" to-layer="763" to-port="1" />
		<edge from-layer="763" from-port="2" to-layer="793" to-port="0" />
		<edge from-layer="763" from-port="2" to-layer="765" to-port="0" />
		<edge from-layer="764" from-port="0" to-layer="765" to-port="1" />
		<edge from-layer="765" from-port="2" to-layer="767" to-port="0" />
		<edge from-layer="766" from-port="0" to-layer="767" to-port="1" />
		<edge from-layer="767" from-port="2" to-layer="769" to-port="0" />
		<edge from-layer="768" from-port="0" to-layer="769" to-port="1" />
		<edge from-layer="769" from-port="2" to-layer="778" to-port="0" />
		<edge from-layer="770" from-port="0" to-layer="771" to-port="0" />
		<edge from-layer="771" from-port="1" to-layer="774" to-port="0" />
		<edge from-layer="772" from-port="0" to-layer="773" to-port="0" />
		<edge from-layer="773" from-port="1" to-layer="774" to-port="1" />
		<edge from-layer="774" from-port="2" to-layer="776" to-port="0" />
		<edge from-layer="775" from-port="0" to-layer="776" to-port="1" />
		<edge from-layer="776" from-port="2" to-layer="777" to-port="0" />
		<edge from-layer="777" from-port="1" to-layer="778" to-port="1" />
		<edge from-layer="778" from-port="2" to-layer="780" to-port="0" />
		<edge from-layer="779" from-port="0" to-layer="780" to-port="1" />
		<edge from-layer="780" from-port="2" to-layer="781" to-port="0" />
		<edge from-layer="781" from-port="1" to-layer="790" to-port="0" />
		<edge from-layer="782" from-port="0" to-layer="783" to-port="0" />
		<edge from-layer="783" from-port="1" to-layer="786" to-port="0" />
		<edge from-layer="784" from-port="0" to-layer="785" to-port="0" />
		<edge from-layer="785" from-port="1" to-layer="786" to-port="1" />
		<edge from-layer="786" from-port="2" to-layer="788" to-port="0" />
		<edge from-layer="787" from-port="0" to-layer="788" to-port="1" />
		<edge from-layer="788" from-port="2" to-layer="789" to-port="0" />
		<edge from-layer="789" from-port="1" to-layer="790" to-port="1" />
		<edge from-layer="790" from-port="2" to-layer="792" to-port="0" />
		<edge from-layer="791" from-port="0" to-layer="792" to-port="1" />
		<edge from-layer="792" from-port="2" to-layer="793" to-port="1" />
		<edge from-layer="793" from-port="2" to-layer="795" to-port="0" />
		<edge from-layer="794" from-port="0" to-layer="795" to-port="1" />
		<edge from-layer="795" from-port="2" to-layer="797" to-port="0" />
		<edge from-layer="796" from-port="0" to-layer="797" to-port="1" />
		<edge from-layer="797" from-port="2" to-layer="799" to-port="0" />
		<edge from-layer="798" from-port="0" to-layer="799" to-port="1" />
		<edge from-layer="799" from-port="2" to-layer="800" to-port="0" />
		<edge from-layer="800" from-port="2" to-layer="817" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2026.0.0-20965-c6d6a13a886-releases/2026/0" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<nncf>
			<friendly_names_were_updated value="True" />
			<version value="3.0.0" />
			<weight_compression>
				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, '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}, 'backend_params': {}, 'codebook': None, 'adaptive_codebook_params': {'value_type': 'f8e4m3', 'across_blocks': False, 'num_elements': 16}}" />
				<all_layers value="False" />
				<awq value="False" />
				<backup_mode value="int8_asym" />
				<compression_format value="dequantize" />
				<gptq value="False" />
				<group_size value="-1" />
				<ignored_scope value="[]" />
				<lora_correction value="False" />
				<mode value="int8_asym" />
				<ratio value="1.0" />
				<scale_estimation value="False" />
				<sensitivity_metric value="weight_quantization_error" />
			</weight_compression>
		</nncf>
		<optimum>
			<nncf_version value="3.0.0" />
			<optimum_intel_version value="1.27.0" />
			<optimum_version value="2.1.0" />
			<pytorch_version value="2.11.0" />
			<transformers_version value="4.57.6" />
		</optimum>
		<runtime_options>
			<ACTIVATIONS_SCALE_FACTOR value="8.0" />
		</runtime_options>
	</rt_info>
</net>