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_10897" type="Parameter" version="opset1">
			<data shape="?,?,512" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="encoder_hidden_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</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.1.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="0" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.encoder_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="self.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="5" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="356">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="Constant_23097" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="7" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="358,key_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="9" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="364">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="ReadValue_25222" type="ReadValue" version="opset6">
			<data variable_id="364" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="524336" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.encoder_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="self.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="13" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="Constant_22040_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="1048624" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="Constant_22040" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="16" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="239">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="Constant_23090" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="18" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="241,value_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="20" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="244">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="21" name="ReadValue_25220" type="ReadValue" version="opset6">
			<data variable_id="244" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="1049648" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.encoder_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="self.model.decoder.layers.2.encoder_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="24" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="Constant_22072_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="1573936" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="26" name="Constant_22072" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="27" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="483">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="Constant_23106" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="29" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="485,value_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="31" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="488">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="ReadValue_25218" type="ReadValue" version="opset6">
			<data variable_id="488" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="self.model.decoder.layers.4.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="1574960" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.encoder_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="self.model.decoder.layers.4.encoder_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="__module.model.decoder.layers.4.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="Constant_22104_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="2099248" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="Constant_22104" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="__module.model.decoder.layers.4.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="727">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="Constant_23122" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="__module.model.decoder.layers.4.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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="729,value_states.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="732">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="ReadValue_25216" type="ReadValue" version="opset6">
			<data variable_id="732" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="2100272" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.encoder_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="self.model.decoder.layers.3.encoder_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="46" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="Constant_22088_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="2624560" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="Constant_22088" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="49" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="605">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="Constant_23114" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="51" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="607,value_states.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="53" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="610">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="ReadValue_25214" type="ReadValue" version="opset6">
			<data variable_id="610" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="self.model.decoder.layers.5.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="2625584" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.encoder_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="self.model.decoder.layers.5.encoder_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="__module.model.decoder.layers.5.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="Constant_22120_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="3149872" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="Constant_22120" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="60" name="__module.model.decoder.layers.5.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="849">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="Constant_23130" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="__module.model.decoder.layers.5.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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="851,value_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="854">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="ReadValue_25212" type="ReadValue" version="opset6">
			<data variable_id="854" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="3150896" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.encoder_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="self.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="__module.model.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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="234">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="Constant_23089" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="70" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="236,key_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="72" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="242">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="73" name="ReadValue_25210" type="ReadValue" version="opset6">
			<data variable_id="242" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="3675184" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.encoder_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="self.model.decoder.layers.2.encoder_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="76" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="478">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="Constant_23105" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="78" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="480,key_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="80" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="486">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="ReadValue_25208" type="ReadValue" version="opset6">
			<data variable_id="486" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="82" name="self.model.decoder.layers.4.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="4199472" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.encoder_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="self.model.decoder.layers.4.encoder_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="__module.model.decoder.layers.4.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="722">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="Constant_23121" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="__module.model.decoder.layers.4.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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="724,key_states.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="730">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="ReadValue_25206" type="ReadValue" version="opset6">
			<data variable_id="730" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="4723760" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.encoder_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="self.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="92" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="Constant_22056_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="5248048" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="Constant_22056" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="95" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="361">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="Constant_23098" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="97" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="363,value_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="99" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="366">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="ReadValue_25204" type="ReadValue" version="opset6">
			<data variable_id="366" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="5249072" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.encoder_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="self.model.decoder.layers.3.encoder_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="103" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="600">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="Constant_23113" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="105" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="602,key_states.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="107" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="608">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="ReadValue_25202" type="ReadValue" version="opset6">
			<data variable_id="608" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="self.model.decoder.layers.5.encoder_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="5773360" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.encoder_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="self.model.decoder.layers.5.encoder_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="__module.model.decoder.layers.5.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="844">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="Constant_23129" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="__module.model.decoder.layers.5.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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="846,key_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="852">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="ReadValue_25200" type="ReadValue" version="opset6">
			<data variable_id="852" variable_type="dynamic" variable_shape="..." />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="Constant_24772_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="118" name="Constant_24772" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="119" name="ShapeOf_24758" 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="120" name="Constant_24760" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="Constant_24762" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="122" name="Gather_24763" 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">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="Constant_24765" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="124" name="Constant_24767" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="Constant_24769" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="Concat_24770" 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="127" name="Broadcast_24773" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="ReadValue_24488" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.5.decoder.valuepresent.5.decoder.value" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.5.decoder.value">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="Constant_24196" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="130" name="Gather_24197" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="self.model.decoder.embed_tokens.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="51865, 512" offset="6297674" size="53109760" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.embed_tokens.weight">
					<dim>51865</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="self.model.decoder.embed_tokens.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>51865</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>51865</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="Constant_23083" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="59407434" size="16" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="134" 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="109,input.1">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="135" 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="136" name="__module.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59407450" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="137" name="__module.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>51865</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="111,inputs_embeds">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="self.model.decoder.embed_positions.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="448, 512" offset="59407454" size="458752" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.embed_positions.weight">
					<dim>448</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="self.model.decoder.embed_positions.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>448</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="Constant_24784_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="141" name="Constant_24784" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="142" name="Constant_24777" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="Constant_24779" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="Constant_24781" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="Concat_24782" 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="146" name="Broadcast_24785" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="ReadValue_24466" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.0.decoder.keypresent.0.decoder.key" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="Constant_24163" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="149" name="Gather_24164" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="ShapeOf_22505" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="Constant_22506" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="59866206" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="152" name="Constant_22507" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="153" name="Gather_22508" 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="112,128" />
			</output>
		</layer>
		<layer id="154" name="ShapeOf_22495" 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="155" name="Constant_22496" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="59866214" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="156" name="Constant_22497" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="157" name="Gather_22498" 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="106" />
			</output>
		</layer>
		<layer id="158" 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="114" />
			</output>
		</layer>
		<layer id="159" name="__module.model.decoder/aten::arange/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59866222" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="160" 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="116,cache_position">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="64" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" names="64" />
			</output>
		</layer>
		<layer id="162" 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="117,135">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="Constant_22510" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="Constant_22511" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="165" name="Gather_22512" 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="105,133,168,223,290,345,412,467,534,589,656,711,778,833">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="Constant_11458" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="59866214" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="167" 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="118">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="168" 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="119,position_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="169" 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="170" name="__module.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59407450" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="171" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="122,123,positions,positions.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="172" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="124,input.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="173" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="174" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="Constant_22030_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="59866230" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="Constant_22030" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="177" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="Constant_22031_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="59867254" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="Constant_22031" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="180" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="163,hidden_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="181" name="self.model.decoder.layers.0.self_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="59868278" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.self_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="self.model.decoder.layers.0.self_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="183" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="Constant_22032_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="Constant_22032" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="Multiply_21723" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="Constant_22033_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="60392568" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="Constant_22033" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="189" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="173,query_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="Constant_23084" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="191" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="175,query_states.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="193" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="176">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="self.model.decoder.layers.0.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="60393592" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.self_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="self.model.decoder.layers.0.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="196" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="179">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="Constant_23085" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="198" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="181,key_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="200" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="187">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="201" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.1">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="Constant_24796_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="203" name="Constant_24796" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="204" name="Constant_24789" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="Constant_24791" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="Constant_24793" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="Concat_24794" 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="208" name="Broadcast_24797" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="ReadValue_24468" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.0.decoder.valuepresent.0.decoder.value" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="Constant_24166" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="211" name="Gather_24167" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="self.model.decoder.layers.0.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="60917880" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.self_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="self.model.decoder.layers.0.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="214" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="Constant_22034_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="61442168" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="Constant_22034" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="217" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="184">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="218" name="Constant_23086" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="219" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="186,value_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="221" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="189">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="222" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.1">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="__module.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59407450" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="224" name="Constant_22523" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="59866214" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="Reshape_22524" 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="226" name="__module.model.decoder/aten::size/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59407450" size="4" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="227" 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="126,134" />
			</output>
		</layer>
		<layer id="228" 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="130,131,kv_length" />
			</output>
		</layer>
		<layer id="229" name="__module.model.decoder/aten::arange/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59866222" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="230" 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="139">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="231" 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="140">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="65" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="59866214" size="8" />
			<output>
				<port id="0" precision="I64" names="65" />
			</output>
		</layer>
		<layer id="233" 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="141">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="69" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="59866206" size="8" />
			<output>
				<port id="0" precision="I64" names="69" />
			</output>
		</layer>
		<layer id="235" 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="142,143,144,kv_idx">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="236" 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="136,137">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="75" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="61443192" size="8" />
			<output>
				<port id="0" precision="I64" names="75" />
			</output>
		</layer>
		<layer id="238" 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="138,q_idx">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="239" 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="145,causal_mask">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="Constant_19045" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="59866214" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="Constant_7341" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="59407450" size="4" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="242" name="Unsqueeze_7342" 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="243" 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="244" 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="147,mask">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="__module.model.decoder/aten::to/Convert_1_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" names="148" />
			</output>
		</layer>
		<layer id="246" name="__module.model.decoder/aten::to/Convert_1" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="247" name="__module.model.decoder/aten::to/Convert_2_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="61443200" size="2" />
			<output>
				<port id="0" precision="FP16" names="150" />
			</output>
		</layer>
		<layer id="248" name="__module.model.decoder/aten::to/Convert_2" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="249" 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="152,196,197,198,318,319,320,440,441,442,562,563,564,684,685,686,806,807,808,attention_mask.3">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="250" name="Constant_7589" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="Constant_22535" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="59866214" size="8" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="252" name="Reshape_22536" 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="253" name="Add_22539" 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="195,317,439,561,683,805">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="254" name="Constant_7592" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="59866214" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="Constant_7587" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="61443192" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="256" 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="199,321,443,565,687,809,attention_mask,attention_mask.11,attention_mask.13,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="257" name="__module.model.decoder.layers.0.self_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="61443202" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="258" name="__module.model.decoder.layers.0.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="259" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="200,attn_output.1">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="__module.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="261" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="201">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="Constant_23087" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="263" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="204">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="self.model.decoder.layers.0.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="61443228" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.self_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="self.model.decoder.layers.0.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="266" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="Constant_22035_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="61967516" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="Constant_22035" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="269" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="208,input.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="270" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="214,input.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="271" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="272" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="Constant_22036_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="61968540" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="Constant_22036" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="275" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="Constant_22037_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="61969564" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="Constant_22037" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="278" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="218,hidden_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="61970588" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.encoder_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="self.model.decoder.layers.0.encoder_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="281" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="Constant_22038_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="Constant_22038" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="Multiply_21727" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="Constant_22039_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="62494876" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="Constant_22039" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="287" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="228,query_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="Constant_23088" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="289" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="230,query_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="291" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="231">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="__module.model.decoder.layers.0.encoder_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="293" name="__module.model.decoder.layers.0.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="294" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="246,attn_output.5">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="__module.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="296" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="247">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="Constant_23091" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="298" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="250">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="62495900" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.encoder_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="self.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="301" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="Constant_22041_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="63020188" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="Constant_22041" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="304" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="254,input.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="305" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="256,input.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="__module.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="307" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="Constant_22042_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="63021212" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="Constant_22042" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="310" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="Constant_22043_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="63022236" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="Constant_22043" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="313" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="260,input.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="self.model.decoder.layers.0.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 512" offset="63023260" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.fc1.weight">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="self.model.decoder.layers.0.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="316" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="Constant_22044_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 2048" offset="65120412" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="Constant_22044" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="319" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="263,input.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="320" 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>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="264,input.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="self.model.decoder.layers.0.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 2048" offset="65124508" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.0.fc2.weight">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="self.model.decoder.layers.0.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="323" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="324" name="Constant_22045_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="67221660" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="325" name="Constant_22045" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="326" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="268,input.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="327" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="270,input.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="328" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="329" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="330" name="Constant_22046_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="67222684" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="331" name="Constant_22046" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="332" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="333" name="Constant_22047_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="67223708" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="Constant_22047" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="335" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="285,hidden_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="self.model.decoder.layers.1.self_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="67224732" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.self_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="self.model.decoder.layers.1.self_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="338" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="Constant_22048_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="Constant_22048" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="Multiply_21731" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="Constant_22049_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="67749020" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="Constant_22049" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="344" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="295,query_states.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="345" name="Constant_23092" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="346" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="297,query_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="348" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="298">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="Constant_24820_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="350" name="Constant_24820" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="351" name="Constant_24813" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="Constant_24815" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="353" name="Constant_24817" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="Concat_24818" 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="355" name="Broadcast_24821" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="ReadValue_24470" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.1.decoder.keypresent.1.decoder.key" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="Constant_24169" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="358" name="Gather_24170" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="self.model.decoder.layers.1.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="67750044" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.self_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="self.model.decoder.layers.1.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="361" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="301">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="362" name="Constant_23093" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="363" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="303,key_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="365" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="309">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="366" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.5">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="367" name="Constant_24808_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="368" name="Constant_24808" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="369" name="Constant_24801" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="370" name="Constant_24803" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="371" name="Constant_24805" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="372" name="Concat_24806" 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="373" name="Broadcast_24809" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="374" name="ReadValue_24472" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.1.decoder.valuepresent.1.decoder.value" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="375" name="Constant_24172" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="376" name="Gather_24173" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="377" name="self.model.decoder.layers.1.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="68274332" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.self_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="378" name="self.model.decoder.layers.1.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="379" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="380" name="Constant_22050_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="68798620" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="381" name="Constant_22050" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="382" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="306">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="383" name="Constant_23094" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="384" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="308,value_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="385" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="386" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="311">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="387" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.5">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="388" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="322,attn_output.9">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="389" name="__module.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="390" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="323">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="391" name="Constant_23095" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="392" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="326">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="393" name="self.model.decoder.layers.1.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="68799644" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.self_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="394" name="self.model.decoder.layers.1.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="395" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="396" name="Constant_22051_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="69323932" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="397" name="Constant_22051" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="398" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="330,input.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="399" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="336,input.37">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="400" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="401" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="402" name="Constant_22052_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="69324956" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="403" name="Constant_22052" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="404" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="405" name="Constant_22053_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="69325980" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="406" name="Constant_22053" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="407" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="340,hidden_states.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="408" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="69327004" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.encoder_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="409" name="self.model.decoder.layers.1.encoder_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="410" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="411" name="Constant_22054_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="412" name="Constant_22054" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="413" name="Multiply_21735" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="414" name="Constant_22055_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="69851292" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="415" name="Constant_22055" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="416" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="350,query_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="417" name="Constant_23096" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="418" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="352,query_states.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="419" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="420" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="353">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="421" name="__module.model.decoder.layers.1.encoder_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="422" name="__module.model.decoder.layers.1.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="423" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="368,attn_output.13">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="424" name="__module.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="425" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="369">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="426" name="Constant_23099" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="427" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="372">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="428" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="69852316" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.encoder_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="429" name="self.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="430" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="431" name="Constant_22057_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="70376604" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="432" name="Constant_22057" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="433" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="376,input.41">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="434" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="378,input.43">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="435" name="__module.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="436" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="437" name="Constant_22058_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="70377628" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="438" name="Constant_22058" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="439" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="440" name="Constant_22059_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="70378652" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="441" name="Constant_22059" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="442" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="382,input.45">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="443" name="self.model.decoder.layers.1.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 512" offset="70379676" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.fc1.weight">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="444" name="self.model.decoder.layers.1.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="445" name="__module.model.decoder.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="446" name="Constant_22060_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 2048" offset="72476828" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="447" name="Constant_22060" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="448" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="385,input.47">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="449" 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>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="386,input.49">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="450" name="self.model.decoder.layers.1.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 2048" offset="72480924" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.1.fc2.weight">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="451" name="self.model.decoder.layers.1.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="452" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="453" name="Constant_22061_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="74578076" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="454" name="Constant_22061" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="455" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="390,input.53">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="456" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="392,input.55">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="457" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="458" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="459" name="Constant_22062_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="74579100" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="460" name="Constant_22062" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="461" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="462" name="Constant_22063_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="74580124" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="463" name="Constant_22063" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="464" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="407,hidden_states.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="465" name="self.model.decoder.layers.2.self_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="74581148" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.self_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="466" name="self.model.decoder.layers.2.self_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="467" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="468" name="Constant_22064_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="469" name="Constant_22064" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="470" name="Multiply_21739" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="471" name="Constant_22065_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="75105436" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="472" name="Constant_22065" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="473" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="417,query_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="474" name="Constant_23100" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="475" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="419,query_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="476" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="477" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="420">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="478" name="Constant_24844_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="479" name="Constant_24844" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="480" name="Constant_24837" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="481" name="Constant_24839" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="482" name="Constant_24841" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="483" name="Concat_24842" 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="484" name="Broadcast_24845" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="485" name="ReadValue_24474" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.2.decoder.keypresent.2.decoder.key" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="486" name="Constant_24175" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="487" name="Gather_24176" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="488" name="self.model.decoder.layers.2.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="75106460" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.self_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="489" name="self.model.decoder.layers.2.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="490" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="423">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="491" name="Constant_23101" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="492" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="425,key_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="493" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="494" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="431">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="495" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.9">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="496" name="Constant_24832_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="497" name="Constant_24832" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="498" name="Constant_24825" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="499" name="Constant_24827" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="500" name="Constant_24829" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="501" name="Concat_24830" 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="502" name="Broadcast_24833" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="503" name="ReadValue_24476" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.2.decoder.valuepresent.2.decoder.value" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="504" name="Constant_24178" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="505" name="Gather_24179" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="506" name="self.model.decoder.layers.2.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="75630748" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.self_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="507" name="self.model.decoder.layers.2.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="508" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="509" name="Constant_22066_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="76155036" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="510" name="Constant_22066" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="511" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="428">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="512" name="Constant_23102" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="513" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="430,value_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="514" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="515" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="433">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="516" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.9">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="517" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="444,attn_output.17">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="518" name="__module.model.decoder.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="519" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="445">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="520" name="Constant_23103" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="521" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="448">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="522" name="self.model.decoder.layers.2.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="76156060" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.self_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="523" name="self.model.decoder.layers.2.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="524" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="525" name="Constant_22067_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="76680348" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="526" name="Constant_22067" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="527" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="452,input.59">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="528" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="458,input.61">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="529" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="530" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="531" name="Constant_22068_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="76681372" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="532" name="Constant_22068" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="533" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="534" name="Constant_22069_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="76682396" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="535" name="Constant_22069" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="536" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="462,hidden_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="537" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="76683420" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.encoder_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="538" name="self.model.decoder.layers.2.encoder_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="539" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="540" name="Constant_22070_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="541" name="Constant_22070" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="542" name="Multiply_21743" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="543" name="Constant_22071_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="77207708" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="544" name="Constant_22071" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="545" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="472,query_states.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="546" name="Constant_23104" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="547" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="474,query_states.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="548" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="549" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="475">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="550" name="__module.model.decoder.layers.2.encoder_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="551" name="__module.model.decoder.layers.2.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="552" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="490,attn_output.21">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="553" name="__module.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="554" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="491">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="555" name="Constant_23107" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="556" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="494">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="557" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="77208732" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.encoder_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="558" name="self.model.decoder.layers.2.encoder_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="559" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="560" name="Constant_22073_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="77733020" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="561" name="Constant_22073" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="562" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="498,input.65">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="563" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="500,input.67">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="564" name="__module.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="565" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="566" name="Constant_22074_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="77734044" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="567" name="Constant_22074" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="568" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="569" name="Constant_22075_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="77735068" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="570" name="Constant_22075" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="571" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="504,input.69">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="572" name="self.model.decoder.layers.2.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 512" offset="77736092" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.fc1.weight">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="573" name="self.model.decoder.layers.2.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="574" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="575" name="Constant_22076_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 2048" offset="79833244" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="576" name="Constant_22076" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="577" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="507,input.71">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="578" 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>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="508,input.73">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="579" name="self.model.decoder.layers.2.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 2048" offset="79837340" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.2.fc2.weight">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="580" name="self.model.decoder.layers.2.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="581" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="582" name="Constant_22077_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="81934492" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="583" name="Constant_22077" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="584" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="512,input.77">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="585" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="514,input.79">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="586" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="587" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="588" name="Constant_22078_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="81935516" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="589" name="Constant_22078" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="590" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="591" name="Constant_22079_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="81936540" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="592" name="Constant_22079" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="593" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="529,hidden_states.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="594" name="self.model.decoder.layers.3.self_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="81937564" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.self_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="595" name="self.model.decoder.layers.3.self_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="596" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="597" name="Constant_22080_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="598" name="Constant_22080" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="599" name="Multiply_21747" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="600" name="Constant_22081_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="82461852" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="601" name="Constant_22081" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="602" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="539,query_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="603" name="Constant_23108" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="604" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="541,query_states.27">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="605" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="606" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="542">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="607" name="Constant_24868_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="608" name="Constant_24868" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="609" name="Constant_24861" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="610" name="Constant_24863" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="611" name="Constant_24865" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="612" name="Concat_24866" 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="613" name="Broadcast_24869" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="614" name="ReadValue_24478" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.3.decoder.keypresent.3.decoder.key" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="615" name="Constant_24181" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="616" name="Gather_24182" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="617" name="self.model.decoder.layers.3.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="82462876" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.self_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="618" name="self.model.decoder.layers.3.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="619" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="545">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="620" name="Constant_23109" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="621" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="547,key_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="622" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="623" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="553">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="624" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.13">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="625" name="Constant_24856_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="626" name="Constant_24856" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="627" name="Constant_24849" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="628" name="Constant_24851" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="629" name="Constant_24853" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="630" name="Concat_24854" 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="631" name="Broadcast_24857" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="632" name="ReadValue_24480" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.3.decoder.valuepresent.3.decoder.value" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="633" name="Constant_24184" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="634" name="Gather_24185" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="635" name="self.model.decoder.layers.3.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="82987164" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.self_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="636" name="self.model.decoder.layers.3.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="637" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="638" name="Constant_22082_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="83511452" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="639" name="Constant_22082" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="640" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="550">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="641" name="Constant_23110" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="642" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="552,value_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="643" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="644" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="555">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="645" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.13">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="646" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="566,attn_output.25">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="647" name="__module.model.decoder.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="648" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="567">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="649" name="Constant_23111" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="650" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="570">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="651" name="self.model.decoder.layers.3.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="83512476" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.self_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="652" name="self.model.decoder.layers.3.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="653" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="654" name="Constant_22083_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="84036764" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="655" name="Constant_22083" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="656" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="574,input.83">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="657" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="580,input.85">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="658" 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="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="659" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="660" name="Constant_22084_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="84037788" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="661" name="Constant_22084" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="662" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="663" name="Constant_22085_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="84038812" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="664" name="Constant_22085" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="665" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="584,hidden_states.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="666" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="84039836" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.encoder_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="667" name="self.model.decoder.layers.3.encoder_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="668" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="669" name="Constant_22086_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="670" name="Constant_22086" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="671" name="Multiply_21751" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="672" name="Constant_22087_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="84564124" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="673" name="Constant_22087" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="674" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="594,query_states.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="675" name="Constant_23112" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="676" 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>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="596,query_states.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="677" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="678" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="597">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="679" name="__module.model.decoder.layers.3.encoder_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="680" name="__module.model.decoder.layers.3.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="681" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="612,attn_output.29">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="682" name="__module.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="683" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="613">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="684" name="Constant_23115" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="685" 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>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="616">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="686" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="84565148" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.encoder_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="687" name="self.model.decoder.layers.3.encoder_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="688" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="689" name="Constant_22089_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="85089436" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="690" name="Constant_22089" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="691" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="620,input.89">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="692" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="622,input.91">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="693" name="__module.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="694" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="695" name="Constant_22090_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="85090460" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="696" name="Constant_22090" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="697" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="698" name="Constant_22091_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="85091484" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="699" name="Constant_22091" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="700" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="626,input.93">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="701" name="self.model.decoder.layers.3.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 512" offset="85092508" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.fc1.weight">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="702" name="self.model.decoder.layers.3.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="703" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="704" name="Constant_22092_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 2048" offset="87189660" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="705" name="Constant_22092" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="706" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="629,input.95">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="707" 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>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="630,input.97">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="708" name="self.model.decoder.layers.3.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 2048" offset="87193756" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.3.fc2.weight">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="709" name="self.model.decoder.layers.3.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="710" 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>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="711" name="Constant_22093_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="89290908" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="712" name="Constant_22093" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="713" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="634,input.101">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="714" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="636,input.103">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="715" name="__module.model.decoder.layers.4.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="716" name="__module.model.decoder.layers.4.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="717" name="Constant_22094_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="89291932" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="718" name="Constant_22094" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="719" name="__module.model.decoder.layers.4.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="720" name="Constant_22095_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="89292956" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="721" name="Constant_22095" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="722" name="__module.model.decoder.layers.4.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="651,hidden_states.41">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="723" name="self.model.decoder.layers.4.self_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="89293980" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.self_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="724" name="self.model.decoder.layers.4.self_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="725" name="__module.model.decoder.layers.4.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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="726" name="Constant_22096_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="727" name="Constant_22096" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="728" name="Multiply_21755" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="729" name="Constant_22097_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="89818268" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="730" name="Constant_22097" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="731" name="__module.model.decoder.layers.4.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="661,query_states.33">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="732" name="Constant_23116" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="733" name="__module.model.decoder.layers.4.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="663,query_states.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="734" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="735" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="664">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="736" name="Constant_24892_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="737" name="Constant_24892" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="738" name="Constant_24885" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="739" name="Constant_24887" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="740" name="Constant_24889" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="741" name="Concat_24890" 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="742" name="Broadcast_24893" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="743" name="ReadValue_24482" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.4.decoder.keypresent.4.decoder.key" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.4.decoder.key">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="744" name="Constant_24187" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="745" name="Gather_24188" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="746" name="self.model.decoder.layers.4.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="89819292" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.self_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="747" name="self.model.decoder.layers.4.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="748" name="__module.model.decoder.layers.4.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="667">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="749" name="Constant_23117" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="750" name="__module.model.decoder.layers.4.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="669,key_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="751" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="752" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="675">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="753" name="__module.model.decoder.layers.4.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.17">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="754" name="Constant_24880_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="755" name="Constant_24880" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="756" name="Constant_24873" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="757" name="Constant_24875" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="758" name="Constant_24877" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="759" name="Concat_24878" 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="760" name="Broadcast_24881" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="761" name="ReadValue_24484" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.4.decoder.valuepresent.4.decoder.value" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.4.decoder.value">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="762" name="Constant_24190" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="763" name="Gather_24191" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="764" name="self.model.decoder.layers.4.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="90343580" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.self_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="765" name="self.model.decoder.layers.4.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="766" name="__module.model.decoder.layers.4.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="767" name="Constant_22098_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="90867868" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="768" name="Constant_22098" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="769" name="__module.model.decoder.layers.4.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="672">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="770" name="Constant_23118" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="771" name="__module.model.decoder.layers.4.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="674,value_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="772" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="773" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="677">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="774" name="__module.model.decoder.layers.4.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="value.17">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="775" name="__module.model.decoder.layers.4.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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="688,attn_output.33">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="776" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="777" name="__module.model.decoder.layers.4.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="689">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="778" name="Constant_23119" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="779" name="__module.model.decoder.layers.4.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="692">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="780" name="self.model.decoder.layers.4.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="90868892" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.self_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="781" name="self.model.decoder.layers.4.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="782" name="__module.model.decoder.layers.4.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="783" name="Constant_22099_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="91393180" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="784" name="Constant_22099" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="785" name="__module.model.decoder.layers.4.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="696,input.107">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="786" name="__module.model.decoder.layers.4/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="702,input.109">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="787" name="__module.model.decoder.layers.4.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="788" name="__module.model.decoder.layers.4.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="789" name="Constant_22100_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="91394204" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="790" name="Constant_22100" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="791" name="__module.model.decoder.layers.4.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="792" name="Constant_22101_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="91395228" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="793" name="Constant_22101" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="794" name="__module.model.decoder.layers.4.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="706,hidden_states.45">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="795" name="self.model.decoder.layers.4.encoder_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="91396252" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.encoder_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="796" name="self.model.decoder.layers.4.encoder_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="797" name="__module.model.decoder.layers.4.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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="798" name="Constant_22102_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="799" name="Constant_22102" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="800" name="Multiply_21759" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="801" name="Constant_22103_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="91920540" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="802" name="Constant_22103" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="803" name="__module.model.decoder.layers.4.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="716,query_states.37">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="804" name="Constant_23120" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="805" name="__module.model.decoder.layers.4.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="718,query_states.39">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="806" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="807" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="719">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="808" name="__module.model.decoder.layers.4.encoder_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="809" name="__module.model.decoder.layers.4.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="810" name="__module.model.decoder.layers.4.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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="734,attn_output.37">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="811" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="812" name="__module.model.decoder.layers.4.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="735">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="813" name="Constant_23123" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="814" name="__module.model.decoder.layers.4.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="738">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="815" name="self.model.decoder.layers.4.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="91921564" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.encoder_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="816" name="self.model.decoder.layers.4.encoder_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="817" name="__module.model.decoder.layers.4.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="818" name="Constant_22105_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="92445852" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="819" name="Constant_22105" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="820" name="__module.model.decoder.layers.4.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="742,input.113">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="821" name="__module.model.decoder.layers.4/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="744,input.115">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="822" name="__module.model.decoder.layers.4.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="823" name="__module.model.decoder.layers.4.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="824" name="Constant_22106_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="92446876" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="825" name="Constant_22106" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="826" name="__module.model.decoder.layers.4.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="827" name="Constant_22107_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="92447900" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="828" name="Constant_22107" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="829" name="__module.model.decoder.layers.4.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="748,input.117">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="830" name="self.model.decoder.layers.4.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 512" offset="92448924" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.fc1.weight">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="831" name="self.model.decoder.layers.4.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="832" name="__module.model.decoder.layers.4.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="833" name="Constant_22108_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 2048" offset="94546076" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="834" name="Constant_22108" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="835" name="__module.model.decoder.layers.4.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="751,input.119">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="836" name="__module.model.decoder.layers.4.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="752,input.121">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="837" name="self.model.decoder.layers.4.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 2048" offset="94550172" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.4.fc2.weight">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="838" name="self.model.decoder.layers.4.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="839" name="__module.model.decoder.layers.4.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="840" name="Constant_22109_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="96647324" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="841" name="Constant_22109" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="842" name="__module.model.decoder.layers.4.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="756,input.125">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="843" name="__module.model.decoder.layers.4/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="758,input.127">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="844" name="__module.model.decoder.layers.5.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="845" name="__module.model.decoder.layers.5.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="846" name="Constant_22110_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="96648348" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="847" name="Constant_22110" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="848" name="__module.model.decoder.layers.5.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="849" name="Constant_22111_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="96649372" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="850" name="Constant_22111" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="851" name="__module.model.decoder.layers.5.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="773,hidden_states.51">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="852" name="self.model.decoder.layers.5.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="96650396" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.self_attn.v_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="853" name="self.model.decoder.layers.5.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="854" name="__module.model.decoder.layers.5.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="855" name="Constant_22112_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="97174684" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="856" name="Constant_22112" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="857" name="__module.model.decoder.layers.5.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="794">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="858" name="Constant_23124" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="859" name="__module.model.decoder.layers.5.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="796,value_states.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="860" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="861" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="799">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="862" name="__module.model.decoder.layers.5.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="present.5.decoder.value,value.21">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="863" name="Constant_24904_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="864" name="Constant_24904" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="865" name="Constant_24897" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297658" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="866" name="Constant_24899" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="867" name="Constant_24901" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="6297666" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="868" name="Concat_24902" 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="869" name="Broadcast_24905" 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>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="870" name="ReadValue_24486" type="ReadValue" version="opset6">
			<data variable_id="past_key_values.5.decoder.keypresent.5.decoder.key" variable_type="f32" variable_shape="?,8,?,64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>0</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="past_key_values.5.decoder.key">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="871" name="Constant_24193" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="6297650" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="872" name="Gather_24194" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="873" name="self.model.decoder.layers.5.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="97175708" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.self_attn.k_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="874" name="self.model.decoder.layers.5.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="875" name="__module.model.decoder.layers.5.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="789">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="876" name="Constant_23125" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="877" name="__module.model.decoder.layers.5.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="791,key_states.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="878" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="879" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="797">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="880" name="__module.model.decoder.layers.5.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="key.21">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="881" name="self.model.decoder.layers.5.self_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="97699996" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.self_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="882" name="self.model.decoder.layers.5.self_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="883" name="__module.model.decoder.layers.5.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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="884" name="Constant_22113_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="885" name="Constant_22113" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="886" name="Multiply_21763" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="887" name="Constant_22114_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="98224284" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="888" name="Constant_22114" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="889" name="__module.model.decoder.layers.5.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="783,query_states.41">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="890" name="Constant_23126" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="891" name="__module.model.decoder.layers.5.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="785,query_states.43">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="892" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="893" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="786">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="894" name="__module.model.decoder.layers.5.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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="810,attn_output.41">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="895" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="896" name="__module.model.decoder.layers.5.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="811">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="897" name="Constant_23127" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="898" name="__module.model.decoder.layers.5.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="814">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="899" name="self.model.decoder.layers.5.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="98225308" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.self_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="900" name="self.model.decoder.layers.5.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="901" name="__module.model.decoder.layers.5.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="902" name="Constant_22115_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="98749596" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="903" name="Constant_22115" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="904" name="__module.model.decoder.layers.5.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="818,input.131">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="905" name="__module.model.decoder.layers.5/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="824,input.133">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="906" name="__module.model.decoder.layers.5.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="907" name="__module.model.decoder.layers.5.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="908" name="Constant_22116_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="98750620" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="909" name="Constant_22116" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="910" name="__module.model.decoder.layers.5.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="911" name="Constant_22117_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="98751644" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="912" name="Constant_22117" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="913" name="__module.model.decoder.layers.5.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="828,hidden_states.55">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="914" name="self.model.decoder.layers.5.encoder_attn.q_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="98752668" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.encoder_attn.q_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="915" name="self.model.decoder.layers.5.encoder_attn.q_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="916" name="__module.model.decoder.layers.5.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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="917" name="Constant_22118_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1" offset="60392566" size="2" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="918" name="Constant_22118" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="919" name="Multiply_21767" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="920" name="Constant_22119_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="99276956" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="921" name="Constant_22119" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="922" name="__module.model.decoder.layers.5.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="838,query_states.45">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="923" name="Constant_23128" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="524288" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="924" name="__module.model.decoder.layers.5.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="840,query_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="925" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="926" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="841">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="927" name="__module.model.decoder.layers.5.encoder_attn/aten::scaled_dot_product_attention/ConvertLike_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="" offset="6297648" size="2" />
			<output>
				<port id="0" precision="FP16" />
			</output>
		</layer>
		<layer id="928" name="__module.model.decoder.layers.5.encoder_attn/aten::scaled_dot_product_attention/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16" />
			</input>
			<output>
				<port id="1" precision="FP32" />
			</output>
		</layer>
		<layer id="929" name="__module.model.decoder.layers.5.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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</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="856,attn_output.45">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="930" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="524320" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="931" name="__module.model.decoder.layers.5.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="857">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="932" name="Constant_23131" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="61443204" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="933" name="__module.model.decoder.layers.5.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="860">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="934" name="self.model.decoder.layers.5.encoder_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 512" offset="99277980" size="524288" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.encoder_attn.out_proj.weight">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="935" name="self.model.decoder.layers.5.encoder_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="936" name="__module.model.decoder.layers.5.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="937" name="Constant_22121_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="99802268" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="938" name="Constant_22121" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="939" name="__module.model.decoder.layers.5.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="864,input.137">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="940" name="__module.model.decoder.layers.5/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="866,input.139">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="941" name="__module.model.decoder.layers.5.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="942" name="__module.model.decoder.layers.5.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="943" name="Constant_22122_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="99803292" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="944" name="Constant_22122" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="945" name="__module.model.decoder.layers.5.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="946" name="Constant_22123_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="99804316" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="947" name="Constant_22123" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="948" name="__module.model.decoder.layers.5.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="870,input.141">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="949" name="self.model.decoder.layers.5.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 512" offset="99805340" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.fc1.weight">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="950" name="self.model.decoder.layers.5.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="951" name="__module.model.decoder.layers.5.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="952" name="Constant_22124_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 2048" offset="101902492" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="953" name="Constant_22124" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="954" name="__module.model.decoder.layers.5.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="873,input.143">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="955" name="__module.model.decoder.layers.5.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="874,input.145">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="956" name="self.model.decoder.layers.5.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="512, 2048" offset="101906588" size="2097152" />
			<output>
				<port id="0" precision="FP16" names="self.model.decoder.layers.5.fc2.weight">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="957" name="self.model.decoder.layers.5.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="958" name="__module.model.decoder.layers.5.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="959" name="Constant_22125_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="104003740" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="960" name="Constant_22125" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="961" name="__module.model.decoder.layers.5.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="878,input.149">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="962" name="__module.model.decoder.layers.5/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="880,input.151">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="963" name="__module.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="59866226" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="964" 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>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="965" name="Constant_22126_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="104004764" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="966" name="Constant_22126" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="967" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="968" name="Constant_22127_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 512" offset="104005788" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="969" name="Constant_22127" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="970" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="888,input">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="971" 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>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>51865</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="logits">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51865</dim>
				</port>
			</output>
		</layer>
		<layer id="972" name="Assign_24467" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="973" name="Assign_24469" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="974" name="Assign_24471" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="975" name="Assign_24473" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="976" name="Assign_24475" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="977" name="Assign_24477" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="978" name="Assign_24479" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="979" name="Assign_24481" 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>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="980" name="Assign_24483" type="Assign" version="opset6">
			<data variable_id="past_key_values.4.decoder.keypresent.4.decoder.key" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="981" name="Assign_24485" type="Assign" version="opset6">
			<data variable_id="past_key_values.4.decoder.valuepresent.4.decoder.value" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="982" name="Assign_24487" type="Assign" version="opset6">
			<data variable_id="past_key_values.5.decoder.keypresent.5.decoder.key" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="983" name="Assign_24489" type="Assign" version="opset6">
			<data variable_id="past_key_values.5.decoder.valuepresent.5.decoder.value" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="984" name="Assign_25201" type="Assign" version="opset6">
			<data variable_id="852" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="985" name="Assign_25203" type="Assign" version="opset6">
			<data variable_id="608" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="986" name="Assign_25205" type="Assign" version="opset6">
			<data variable_id="366" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="987" name="Assign_25207" type="Assign" version="opset6">
			<data variable_id="730" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="988" name="Assign_25209" type="Assign" version="opset6">
			<data variable_id="486" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="989" name="Assign_25211" type="Assign" version="opset6">
			<data variable_id="242" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="990" name="Assign_25213" type="Assign" version="opset6">
			<data variable_id="854" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="991" name="Assign_25215" type="Assign" version="opset6">
			<data variable_id="610" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="992" name="Assign_25217" type="Assign" version="opset6">
			<data variable_id="732" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="993" name="Assign_25219" type="Assign" version="opset6">
			<data variable_id="488" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="994" name="Assign_25221" type="Assign" version="opset6">
			<data variable_id="244" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="995" name="Assign_25223" type="Assign" version="opset6">
			<data variable_id="364" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="996" name="Result_10878" type="Result" version="opset1" output_names="logits">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51865</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="119" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="154" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="134" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="5" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="35" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="46" 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="68" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="76" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="84" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="24" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="92" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="103" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="111" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="13" to-port="0" />
		<edge from-layer="2" from-port="0" to-layer="149" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="130" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="211" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="358" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="376" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="487" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="616" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="634" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="745" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="763" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="872" to-port="1" />
		<edge from-layer="2" from-port="0" to-layer="505" 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="5" to-port="1" />
		<edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
		<edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
		<edge from-layer="7" from-port="2" to-layer="9" to-port="0" />
		<edge from-layer="8" from-port="0" to-layer="9" to-port="1" />
		<edge from-layer="9" from-port="2" to-layer="10" to-port="0" />
		<edge from-layer="10" from-port="1" to-layer="995" to-port="0" />
		<edge from-layer="10" from-port="1" to-layer="423" to-port="1" />
		<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
		<edge from-layer="12" from-port="1" to-layer="13" to-port="1" />
		<edge from-layer="13" from-port="2" to-layer="16" to-port="0" />
		<edge from-layer="14" from-port="0" to-layer="15" to-port="0" />
		<edge from-layer="15" from-port="1" to-layer="16" to-port="1" />
		<edge from-layer="16" from-port="2" to-layer="18" to-port="0" />
		<edge from-layer="17" from-port="0" to-layer="18" to-port="1" />
		<edge from-layer="18" from-port="2" to-layer="20" to-port="0" />
		<edge from-layer="19" from-port="0" to-layer="20" to-port="1" />
		<edge from-layer="20" from-port="2" to-layer="21" to-port="0" />
		<edge from-layer="21" from-port="1" to-layer="294" to-port="2" />
		<edge from-layer="21" from-port="1" to-layer="994" to-port="0" />
		<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
		<edge from-layer="23" from-port="1" to-layer="24" to-port="1" />
		<edge from-layer="24" from-port="2" to-layer="27" to-port="0" />
		<edge from-layer="25" from-port="0" to-layer="26" to-port="0" />
		<edge from-layer="26" from-port="1" 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="552" to-port="2" />
		<edge from-layer="32" from-port="1" to-layer="993" to-port="0" />
		<edge from-layer="33" from-port="0" to-layer="34" to-port="0" />
		<edge from-layer="34" from-port="1" to-layer="35" to-port="1" />
		<edge from-layer="35" from-port="2" to-layer="38" to-port="0" />
		<edge from-layer="36" from-port="0" to-layer="37" to-port="0" />
		<edge from-layer="37" from-port="1" to-layer="38" to-port="1" />
		<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
		<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
		<edge from-layer="40" from-port="2" to-layer="42" to-port="0" />
		<edge from-layer="41" from-port="0" to-layer="42" to-port="1" />
		<edge from-layer="42" from-port="2" to-layer="43" to-port="0" />
		<edge from-layer="43" from-port="1" to-layer="810" to-port="2" />
		<edge from-layer="43" from-port="1" to-layer="992" to-port="0" />
		<edge from-layer="44" from-port="0" to-layer="45" to-port="0" />
		<edge from-layer="45" from-port="1" to-layer="46" to-port="1" />
		<edge from-layer="46" from-port="2" to-layer="49" to-port="0" />
		<edge from-layer="47" from-port="0" to-layer="48" to-port="0" />
		<edge from-layer="48" from-port="1" to-layer="49" to-port="1" />
		<edge from-layer="49" from-port="2" to-layer="51" to-port="0" />
		<edge from-layer="50" from-port="0" to-layer="51" to-port="1" />
		<edge from-layer="51" from-port="2" to-layer="53" to-port="0" />
		<edge from-layer="52" from-port="0" to-layer="53" to-port="1" />
		<edge from-layer="53" from-port="2" to-layer="54" to-port="0" />
		<edge from-layer="54" from-port="1" to-layer="681" to-port="2" />
		<edge from-layer="54" from-port="1" to-layer="991" to-port="0" />
		<edge from-layer="55" from-port="0" to-layer="56" to-port="0" />
		<edge from-layer="56" from-port="1" to-layer="57" to-port="1" />
		<edge from-layer="57" from-port="2" to-layer="60" to-port="0" />
		<edge from-layer="58" from-port="0" to-layer="59" to-port="0" />
		<edge from-layer="59" from-port="1" to-layer="60" to-port="1" />
		<edge from-layer="60" from-port="2" to-layer="62" to-port="0" />
		<edge from-layer="61" from-port="0" to-layer="62" to-port="1" />
		<edge from-layer="62" from-port="2" to-layer="64" to-port="0" />
		<edge from-layer="63" from-port="0" to-layer="64" to-port="1" />
		<edge from-layer="64" from-port="2" to-layer="65" to-port="0" />
		<edge from-layer="65" from-port="1" to-layer="990" to-port="0" />
		<edge from-layer="65" from-port="1" to-layer="929" to-port="2" />
		<edge from-layer="66" from-port="0" to-layer="67" to-port="0" />
		<edge from-layer="67" from-port="1" to-layer="68" to-port="1" />
		<edge from-layer="68" from-port="2" to-layer="70" to-port="0" />
		<edge from-layer="69" from-port="0" to-layer="70" to-port="1" />
		<edge from-layer="70" from-port="2" to-layer="72" to-port="0" />
		<edge from-layer="71" from-port="0" to-layer="72" to-port="1" />
		<edge from-layer="72" from-port="2" to-layer="73" to-port="0" />
		<edge from-layer="73" from-port="1" to-layer="294" to-port="1" />
		<edge from-layer="73" from-port="1" to-layer="989" to-port="0" />
		<edge from-layer="74" from-port="0" to-layer="75" to-port="0" />
		<edge from-layer="75" from-port="1" to-layer="76" to-port="1" />
		<edge from-layer="76" from-port="2" to-layer="78" to-port="0" />
		<edge from-layer="77" from-port="0" to-layer="78" to-port="1" />
		<edge from-layer="78" from-port="2" to-layer="80" to-port="0" />
		<edge from-layer="79" from-port="0" to-layer="80" to-port="1" />
		<edge from-layer="80" from-port="2" to-layer="81" to-port="0" />
		<edge from-layer="81" from-port="1" to-layer="552" to-port="1" />
		<edge from-layer="81" from-port="1" to-layer="988" to-port="0" />
		<edge from-layer="82" from-port="0" to-layer="83" to-port="0" />
		<edge from-layer="83" from-port="1" to-layer="84" to-port="1" />
		<edge from-layer="84" from-port="2" to-layer="86" to-port="0" />
		<edge from-layer="85" from-port="0" to-layer="86" to-port="1" />
		<edge from-layer="86" from-port="2" to-layer="88" to-port="0" />
		<edge from-layer="87" from-port="0" to-layer="88" to-port="1" />
		<edge from-layer="88" from-port="2" to-layer="89" to-port="0" />
		<edge from-layer="89" from-port="1" to-layer="810" to-port="1" />
		<edge from-layer="89" from-port="1" to-layer="987" to-port="0" />
		<edge from-layer="90" from-port="0" to-layer="91" to-port="0" />
		<edge from-layer="91" from-port="1" to-layer="92" to-port="1" />
		<edge from-layer="92" from-port="2" to-layer="95" to-port="0" />
		<edge from-layer="93" from-port="0" to-layer="94" to-port="0" />
		<edge from-layer="94" from-port="1" to-layer="95" to-port="1" />
		<edge from-layer="95" from-port="2" to-layer="97" to-port="0" />
		<edge from-layer="96" from-port="0" to-layer="97" to-port="1" />
		<edge from-layer="97" from-port="2" to-layer="99" to-port="0" />
		<edge from-layer="98" from-port="0" to-layer="99" to-port="1" />
		<edge from-layer="99" from-port="2" to-layer="100" to-port="0" />
		<edge from-layer="100" from-port="1" to-layer="423" to-port="2" />
		<edge from-layer="100" from-port="1" to-layer="986" to-port="0" />
		<edge from-layer="101" from-port="0" to-layer="102" to-port="0" />
		<edge from-layer="102" from-port="1" 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="985" to-port="0" />
		<edge from-layer="108" from-port="1" to-layer="681" to-port="1" />
		<edge from-layer="109" from-port="0" to-layer="110" to-port="0" />
		<edge from-layer="110" from-port="1" to-layer="111" to-port="1" />
		<edge from-layer="111" from-port="2" to-layer="113" to-port="0" />
		<edge from-layer="112" from-port="0" to-layer="113" to-port="1" />
		<edge from-layer="113" from-port="2" to-layer="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="984" to-port="0" />
		<edge from-layer="116" from-port="1" to-layer="929" to-port="1" />
		<edge from-layer="117" from-port="0" to-layer="118" to-port="0" />
		<edge from-layer="118" from-port="1" to-layer="127" to-port="0" />
		<edge from-layer="119" from-port="1" to-layer="122" to-port="0" />
		<edge from-layer="120" from-port="0" to-layer="122" to-port="1" />
		<edge from-layer="121" from-port="0" to-layer="122" to-port="2" />
		<edge from-layer="122" from-port="3" to-layer="868" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="741" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="501" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="759" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="630" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="612" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="372" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="483" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="354" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="207" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="126" to-port="0" />
		<edge from-layer="122" from-port="3" to-layer="145" to-port="0" />
		<edge from-layer="123" from-port="0" to-layer="126" to-port="1" />
		<edge from-layer="124" from-port="0" to-layer="126" to-port="2" />
		<edge from-layer="125" from-port="0" to-layer="126" to-port="3" />
		<edge from-layer="126" from-port="4" to-layer="127" to-port="1" />
		<edge from-layer="127" from-port="2" to-layer="128" to-port="0" />
		<edge from-layer="128" from-port="1" to-layer="130" to-port="0" />
		<edge from-layer="129" from-port="0" to-layer="130" to-port="2" />
		<edge from-layer="130" from-port="3" to-layer="862" to-port="0" />
		<edge from-layer="131" from-port="0" to-layer="132" to-port="0" />
		<edge from-layer="132" from-port="1" to-layer="971" to-port="1" />
		<edge from-layer="132" from-port="1" to-layer="137" to-port="0" />
		<edge from-layer="133" from-port="0" to-layer="134" to-port="1" />
		<edge from-layer="134" from-port="2" to-layer="135" to-port="0" />
		<edge from-layer="135" from-port="1" to-layer="137" to-port="1" />
		<edge from-layer="136" from-port="0" to-layer="137" to-port="2" />
		<edge from-layer="137" from-port="3" to-layer="172" 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="171" to-port="0" />
		<edge from-layer="140" from-port="0" to-layer="141" to-port="0" />
		<edge from-layer="141" from-port="1" to-layer="146" to-port="0" />
		<edge from-layer="142" from-port="0" to-layer="145" to-port="1" />
		<edge from-layer="143" from-port="0" to-layer="145" to-port="2" />
		<edge from-layer="144" from-port="0" to-layer="145" to-port="3" />
		<edge from-layer="145" from-port="4" to-layer="146" to-port="1" />
		<edge from-layer="146" from-port="2" to-layer="147" to-port="0" />
		<edge from-layer="147" from-port="1" to-layer="149" to-port="0" />
		<edge from-layer="148" from-port="0" to-layer="149" to-port="2" />
		<edge from-layer="149" from-port="3" to-layer="150" to-port="0" />
		<edge from-layer="149" from-port="3" to-layer="201" 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="153" to-port="1" />
		<edge from-layer="152" from-port="0" to-layer="153" to-port="2" />
		<edge from-layer="153" from-port="3" to-layer="228" to-port="0" />
		<edge from-layer="153" from-port="3" to-layer="252" to-port="0" />
		<edge from-layer="153" from-port="3" to-layer="158" to-port="0" />
		<edge from-layer="153" from-port="3" to-layer="160" to-port="0" />
		<edge from-layer="154" from-port="1" to-layer="165" to-port="0" />
		<edge from-layer="154" from-port="1" to-layer="157" to-port="0" />
		<edge from-layer="155" from-port="0" to-layer="157" to-port="1" />
		<edge from-layer="156" from-port="0" to-layer="157" to-port="2" />
		<edge from-layer="157" from-port="3" to-layer="225" to-port="0" />
		<edge from-layer="157" from-port="3" to-layer="158" to-port="1" />
		<edge from-layer="158" from-port="2" to-layer="160" to-port="1" />
		<edge from-layer="159" from-port="0" to-layer="160" to-port="2" />
		<edge from-layer="160" from-port="3" to-layer="162" to-port="0" />
		<edge from-layer="161" from-port="0" to-layer="162" to-port="1" />
		<edge from-layer="161" from-port="0" to-layer="231" to-port="1" />
		<edge from-layer="162" from-port="2" to-layer="168" to-port="0" />
		<edge from-layer="162" from-port="2" to-layer="236" to-port="0" />
		<edge from-layer="163" from-port="0" to-layer="165" to-port="1" />
		<edge from-layer="164" from-port="0" to-layer="165" to-port="2" />
		<edge from-layer="165" from-port="3" to-layer="167" to-port="0" />
		<edge from-layer="165" from-port="3" to-layer="243" to-port="0" />
		<edge from-layer="166" from-port="0" to-layer="167" to-port="1" />
		<edge from-layer="167" from-port="2" to-layer="168" to-port="1" />
		<edge from-layer="168" from-port="2" to-layer="169" to-port="0" />
		<edge from-layer="169" from-port="1" to-layer="171" to-port="1" />
		<edge from-layer="170" from-port="0" to-layer="171" to-port="2" />
		<edge from-layer="171" from-port="3" to-layer="172" to-port="1" />
		<edge from-layer="172" from-port="2" to-layer="270" to-port="0" />
		<edge from-layer="172" from-port="2" to-layer="174" to-port="0" />
		<edge from-layer="173" from-port="0" to-layer="174" to-port="1" />
		<edge from-layer="174" from-port="2" to-layer="177" to-port="0" />
		<edge from-layer="175" from-port="0" to-layer="176" to-port="0" />
		<edge from-layer="176" from-port="1" to-layer="177" to-port="1" />
		<edge from-layer="177" from-port="2" to-layer="180" to-port="0" />
		<edge from-layer="178" from-port="0" to-layer="179" to-port="0" />
		<edge from-layer="179" from-port="1" to-layer="180" to-port="1" />
		<edge from-layer="180" from-port="2" to-layer="196" to-port="0" />
		<edge from-layer="180" from-port="2" to-layer="214" to-port="0" />
		<edge from-layer="180" from-port="2" to-layer="183" to-port="0" />
		<edge from-layer="181" from-port="0" to-layer="182" to-port="0" />
		<edge from-layer="182" from-port="1" to-layer="183" to-port="1" />
		<edge from-layer="183" from-port="2" to-layer="186" to-port="0" />
		<edge from-layer="184" from-port="0" to-layer="185" to-port="0" />
		<edge from-layer="185" from-port="1" to-layer="186" to-port="1" />
		<edge from-layer="186" from-port="2" 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="193" to-port="0" />
		<edge from-layer="192" from-port="0" to-layer="193" to-port="1" />
		<edge from-layer="193" from-port="2" to-layer="259" to-port="0" />
		<edge from-layer="194" from-port="0" to-layer="195" to-port="0" />
		<edge from-layer="195" from-port="1" to-layer="196" to-port="1" />
		<edge from-layer="196" from-port="2" to-layer="198" to-port="0" />
		<edge from-layer="197" from-port="0" to-layer="198" to-port="1" />
		<edge from-layer="198" from-port="2" to-layer="200" to-port="0" />
		<edge from-layer="199" from-port="0" to-layer="200" to-port="1" />
		<edge from-layer="200" from-port="2" to-layer="201" to-port="1" />
		<edge from-layer="201" from-port="2" to-layer="972" to-port="0" />
		<edge from-layer="201" from-port="2" to-layer="259" to-port="1" />
		<edge from-layer="202" from-port="0" to-layer="203" to-port="0" />
		<edge from-layer="203" from-port="1" to-layer="208" to-port="0" />
		<edge from-layer="204" from-port="0" to-layer="207" to-port="1" />
		<edge from-layer="205" from-port="0" to-layer="207" to-port="2" />
		<edge from-layer="206" from-port="0" to-layer="207" to-port="3" />
		<edge from-layer="207" from-port="4" 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="211" to-port="0" />
		<edge from-layer="210" from-port="0" to-layer="211" to-port="2" />
		<edge from-layer="211" from-port="3" to-layer="222" to-port="0" />
		<edge from-layer="212" from-port="0" to-layer="213" to-port="0" />
		<edge from-layer="213" from-port="1" to-layer="214" to-port="1" />
		<edge from-layer="214" from-port="2" to-layer="217" to-port="0" />
		<edge from-layer="215" from-port="0" to-layer="216" to-port="0" />
		<edge from-layer="216" from-port="1" to-layer="217" to-port="1" />
		<edge from-layer="217" from-port="2" to-layer="219" to-port="0" />
		<edge from-layer="218" from-port="0" to-layer="219" to-port="1" />
		<edge from-layer="219" from-port="2" to-layer="221" to-port="0" />
		<edge from-layer="220" from-port="0" to-layer="221" to-port="1" />
		<edge from-layer="221" from-port="2" to-layer="222" to-port="1" />
		<edge from-layer="222" from-port="2" to-layer="259" to-port="2" />
		<edge from-layer="222" from-port="2" to-layer="973" to-port="0" />
		<edge from-layer="223" from-port="0" to-layer="230" to-port="0" />
		<edge from-layer="224" from-port="0" to-layer="225" to-port="1" />
		<edge from-layer="225" from-port="2" to-layer="227" to-port="0" />
		<edge from-layer="225" from-port="2" to-layer="243" to-port="2" />
		<edge from-layer="225" from-port="2" to-layer="253" to-port="1" />
		<edge from-layer="226" from-port="0" to-layer="227" to-port="1" />
		<edge from-layer="227" from-port="2" to-layer="228" to-port="1" />
		<edge from-layer="228" from-port="2" to-layer="230" to-port="1" />
		<edge from-layer="228" from-port="2" to-layer="242" to-port="0" />
		<edge from-layer="229" from-port="0" to-layer="230" to-port="2" />
		<edge from-layer="230" from-port="3" to-layer="231" to-port="0" />
		<edge from-layer="231" from-port="2" to-layer="233" to-port="0" />
		<edge from-layer="232" from-port="0" to-layer="236" to-port="1" />
		<edge from-layer="232" from-port="0" to-layer="233" to-port="1" />
		<edge from-layer="233" from-port="2" to-layer="235" to-port="0" />
		<edge from-layer="234" from-port="0" to-layer="235" to-port="1" />
		<edge from-layer="235" from-port="2" to-layer="239" to-port="0" />
		<edge from-layer="236" from-port="2" to-layer="238" to-port="0" />
		<edge from-layer="237" from-port="0" to-layer="238" to-port="1" />
		<edge from-layer="238" from-port="2" to-layer="239" to-port="1" />
		<edge from-layer="239" from-port="2" to-layer="244" to-port="0" />
		<edge from-layer="240" from-port="0" to-layer="243" to-port="1" />
		<edge from-layer="241" from-port="0" to-layer="242" to-port="1" />
		<edge from-layer="242" from-port="2" to-layer="243" to-port="3" />
		<edge from-layer="243" from-port="4" to-layer="244" to-port="1" />
		<edge from-layer="244" from-port="2" to-layer="249" to-port="0" />
		<edge from-layer="245" from-port="0" to-layer="246" to-port="0" />
		<edge from-layer="246" from-port="1" to-layer="249" to-port="1" />
		<edge from-layer="247" from-port="0" to-layer="248" to-port="0" />
		<edge from-layer="248" from-port="1" to-layer="249" to-port="2" />
		<edge from-layer="249" from-port="3" to-layer="256" to-port="0" />
		<edge from-layer="250" from-port="0" to-layer="256" to-port="1" />
		<edge from-layer="251" from-port="0" to-layer="252" to-port="1" />
		<edge from-layer="252" from-port="2" to-layer="253" to-port="0" />
		<edge from-layer="253" from-port="2" to-layer="256" to-port="2" />
		<edge from-layer="254" from-port="0" to-layer="256" to-port="3" />
		<edge from-layer="255" from-port="0" to-layer="256" to-port="4" />
		<edge from-layer="256" from-port="5" to-layer="775" to-port="3" />
		<edge from-layer="256" from-port="5" to-layer="259" to-port="3" />
		<edge from-layer="256" from-port="5" to-layer="646" to-port="3" />
		<edge from-layer="256" from-port="5" to-layer="517" to-port="3" />
		<edge from-layer="256" from-port="5" to-layer="894" to-port="3" />
		<edge from-layer="256" from-port="5" to-layer="388" to-port="3" />
		<edge from-layer="257" from-port="0" to-layer="258" to-port="0" />
		<edge from-layer="258" from-port="1" to-layer="259" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="294" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="423" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="388" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="929" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="552" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="517" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="810" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="646" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="681" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="775" to-port="4" />
		<edge from-layer="258" from-port="1" to-layer="894" to-port="4" />
		<edge from-layer="259" from-port="5" to-layer="261" to-port="0" />
		<edge from-layer="260" from-port="0" to-layer="261" to-port="1" />
		<edge from-layer="261" from-port="2" to-layer="263" to-port="0" />
		<edge from-layer="262" from-port="0" to-layer="263" to-port="1" />
		<edge from-layer="263" from-port="2" to-layer="266" to-port="0" />
		<edge from-layer="264" from-port="0" to-layer="265" to-port="0" />
		<edge from-layer="265" from-port="1" to-layer="266" to-port="1" />
		<edge from-layer="266" from-port="2" to-layer="269" to-port="0" />
		<edge from-layer="267" from-port="0" to-layer="268" to-port="0" />
		<edge from-layer="268" from-port="1" to-layer="269" to-port="1" />
		<edge from-layer="269" from-port="2" to-layer="270" to-port="1" />
		<edge from-layer="270" from-port="2" to-layer="272" to-port="0" />
		<edge from-layer="270" from-port="2" to-layer="305" 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="275" 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="275" to-port="1" />
		<edge from-layer="275" from-port="2" to-layer="278" to-port="0" />
		<edge from-layer="276" from-port="0" to-layer="277" to-port="0" />
		<edge from-layer="277" from-port="1" to-layer="278" to-port="1" />
		<edge from-layer="278" from-port="2" to-layer="281" to-port="0" />
		<edge from-layer="279" from-port="0" to-layer="280" to-port="0" />
		<edge from-layer="280" from-port="1" to-layer="281" to-port="1" />
		<edge from-layer="281" from-port="2" to-layer="284" to-port="0" />
		<edge from-layer="282" from-port="0" to-layer="283" to-port="0" />
		<edge from-layer="283" from-port="1" to-layer="284" to-port="1" />
		<edge from-layer="284" from-port="2" to-layer="287" to-port="0" />
		<edge from-layer="285" from-port="0" to-layer="286" to-port="0" />
		<edge from-layer="286" from-port="1" to-layer="287" to-port="1" />
		<edge from-layer="287" from-port="2" to-layer="289" to-port="0" />
		<edge from-layer="288" from-port="0" to-layer="289" to-port="1" />
		<edge from-layer="289" from-port="2" to-layer="291" to-port="0" />
		<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
		<edge from-layer="291" from-port="2" to-layer="294" to-port="0" />
		<edge from-layer="292" from-port="0" to-layer="293" to-port="0" />
		<edge from-layer="293" from-port="1" to-layer="294" to-port="3" />
		<edge from-layer="294" from-port="5" to-layer="296" to-port="0" />
		<edge from-layer="295" from-port="0" to-layer="296" to-port="1" />
		<edge from-layer="296" from-port="2" to-layer="298" to-port="0" />
		<edge from-layer="297" from-port="0" to-layer="298" to-port="1" />
		<edge from-layer="298" from-port="2" to-layer="301" to-port="0" />
		<edge from-layer="299" from-port="0" to-layer="300" to-port="0" />
		<edge from-layer="300" from-port="1" to-layer="301" to-port="1" />
		<edge from-layer="301" from-port="2" to-layer="304" to-port="0" />
		<edge from-layer="302" from-port="0" to-layer="303" to-port="0" />
		<edge from-layer="303" from-port="1" to-layer="304" to-port="1" />
		<edge from-layer="304" from-port="2" to-layer="305" to-port="1" />
		<edge from-layer="305" from-port="2" to-layer="327" to-port="0" />
		<edge from-layer="305" from-port="2" to-layer="307" to-port="0" />
		<edge from-layer="306" from-port="0" to-layer="307" to-port="1" />
		<edge from-layer="307" from-port="2" to-layer="310" to-port="0" />
		<edge from-layer="308" from-port="0" to-layer="309" to-port="0" />
		<edge from-layer="309" from-port="1" to-layer="310" to-port="1" />
		<edge from-layer="310" from-port="2" to-layer="313" to-port="0" />
		<edge from-layer="311" from-port="0" to-layer="312" to-port="0" />
		<edge from-layer="312" from-port="1" to-layer="313" to-port="1" />
		<edge from-layer="313" from-port="2" to-layer="316" to-port="0" />
		<edge from-layer="314" from-port="0" to-layer="315" to-port="0" />
		<edge from-layer="315" from-port="1" to-layer="316" to-port="1" />
		<edge from-layer="316" from-port="2" to-layer="319" to-port="0" />
		<edge from-layer="317" from-port="0" to-layer="318" to-port="0" />
		<edge from-layer="318" from-port="1" to-layer="319" to-port="1" />
		<edge from-layer="319" from-port="2" to-layer="320" to-port="0" />
		<edge from-layer="320" from-port="1" to-layer="323" to-port="0" />
		<edge from-layer="321" from-port="0" to-layer="322" to-port="0" />
		<edge from-layer="322" from-port="1" to-layer="323" to-port="1" />
		<edge from-layer="323" from-port="2" to-layer="326" to-port="0" />
		<edge from-layer="324" from-port="0" to-layer="325" to-port="0" />
		<edge from-layer="325" from-port="1" to-layer="326" to-port="1" />
		<edge from-layer="326" from-port="2" to-layer="327" to-port="1" />
		<edge from-layer="327" from-port="2" to-layer="399" to-port="0" />
		<edge from-layer="327" from-port="2" to-layer="329" to-port="0" />
		<edge from-layer="328" from-port="0" to-layer="329" to-port="1" />
		<edge from-layer="329" from-port="2" to-layer="332" to-port="0" />
		<edge from-layer="330" from-port="0" to-layer="331" to-port="0" />
		<edge from-layer="331" from-port="1" to-layer="332" to-port="1" />
		<edge from-layer="332" from-port="2" to-layer="335" to-port="0" />
		<edge from-layer="333" from-port="0" to-layer="334" to-port="0" />
		<edge from-layer="334" from-port="1" to-layer="335" to-port="1" />
		<edge from-layer="335" from-port="2" to-layer="379" to-port="0" />
		<edge from-layer="335" from-port="2" to-layer="361" to-port="0" />
		<edge from-layer="335" from-port="2" to-layer="338" to-port="0" />
		<edge from-layer="336" from-port="0" to-layer="337" to-port="0" />
		<edge from-layer="337" from-port="1" to-layer="338" to-port="1" />
		<edge from-layer="338" from-port="2" to-layer="341" to-port="0" />
		<edge from-layer="339" from-port="0" to-layer="340" to-port="0" />
		<edge from-layer="340" from-port="1" to-layer="341" to-port="1" />
		<edge from-layer="341" from-port="2" to-layer="344" to-port="0" />
		<edge from-layer="342" from-port="0" to-layer="343" to-port="0" />
		<edge from-layer="343" from-port="1" to-layer="344" to-port="1" />
		<edge from-layer="344" from-port="2" to-layer="346" to-port="0" />
		<edge from-layer="345" from-port="0" to-layer="346" to-port="1" />
		<edge from-layer="346" from-port="2" to-layer="348" to-port="0" />
		<edge from-layer="347" from-port="0" to-layer="348" to-port="1" />
		<edge from-layer="348" from-port="2" to-layer="388" to-port="0" />
		<edge from-layer="349" from-port="0" to-layer="350" to-port="0" />
		<edge from-layer="350" from-port="1" to-layer="355" to-port="0" />
		<edge from-layer="351" from-port="0" to-layer="354" to-port="1" />
		<edge from-layer="352" from-port="0" to-layer="354" to-port="2" />
		<edge from-layer="353" from-port="0" to-layer="354" to-port="3" />
		<edge from-layer="354" from-port="4" to-layer="355" to-port="1" />
		<edge from-layer="355" from-port="2" to-layer="356" to-port="0" />
		<edge from-layer="356" from-port="1" to-layer="358" to-port="0" />
		<edge from-layer="357" from-port="0" to-layer="358" to-port="2" />
		<edge from-layer="358" from-port="3" to-layer="366" to-port="0" />
		<edge from-layer="359" from-port="0" to-layer="360" to-port="0" />
		<edge from-layer="360" from-port="1" to-layer="361" to-port="1" />
		<edge from-layer="361" from-port="2" to-layer="363" to-port="0" />
		<edge from-layer="362" from-port="0" to-layer="363" to-port="1" />
		<edge from-layer="363" from-port="2" to-layer="365" to-port="0" />
		<edge from-layer="364" from-port="0" to-layer="365" to-port="1" />
		<edge from-layer="365" from-port="2" to-layer="366" to-port="1" />
		<edge from-layer="366" from-port="2" to-layer="974" to-port="0" />
		<edge from-layer="366" from-port="2" to-layer="388" to-port="1" />
		<edge from-layer="367" from-port="0" to-layer="368" to-port="0" />
		<edge from-layer="368" from-port="1" to-layer="373" to-port="0" />
		<edge from-layer="369" from-port="0" to-layer="372" to-port="1" />
		<edge from-layer="370" from-port="0" to-layer="372" to-port="2" />
		<edge from-layer="371" from-port="0" to-layer="372" to-port="3" />
		<edge from-layer="372" from-port="4" to-layer="373" to-port="1" />
		<edge from-layer="373" from-port="2" to-layer="374" to-port="0" />
		<edge from-layer="374" from-port="1" to-layer="376" to-port="0" />
		<edge from-layer="375" from-port="0" to-layer="376" to-port="2" />
		<edge from-layer="376" from-port="3" to-layer="387" to-port="0" />
		<edge from-layer="377" from-port="0" to-layer="378" to-port="0" />
		<edge from-layer="378" from-port="1" to-layer="379" to-port="1" />
		<edge from-layer="379" from-port="2" to-layer="382" to-port="0" />
		<edge from-layer="380" from-port="0" to-layer="381" to-port="0" />
		<edge from-layer="381" from-port="1" to-layer="382" to-port="1" />
		<edge from-layer="382" from-port="2" to-layer="384" to-port="0" />
		<edge from-layer="383" from-port="0" to-layer="384" to-port="1" />
		<edge from-layer="384" from-port="2" to-layer="386" to-port="0" />
		<edge from-layer="385" from-port="0" to-layer="386" to-port="1" />
		<edge from-layer="386" from-port="2" to-layer="387" to-port="1" />
		<edge from-layer="387" from-port="2" to-layer="388" to-port="2" />
		<edge from-layer="387" from-port="2" to-layer="975" to-port="0" />
		<edge from-layer="388" from-port="5" to-layer="390" to-port="0" />
		<edge from-layer="389" from-port="0" to-layer="390" to-port="1" />
		<edge from-layer="390" from-port="2" to-layer="392" to-port="0" />
		<edge from-layer="391" from-port="0" to-layer="392" to-port="1" />
		<edge from-layer="392" from-port="2" to-layer="395" to-port="0" />
		<edge from-layer="393" from-port="0" to-layer="394" to-port="0" />
		<edge from-layer="394" from-port="1" to-layer="395" to-port="1" />
		<edge from-layer="395" from-port="2" to-layer="398" to-port="0" />
		<edge from-layer="396" from-port="0" to-layer="397" to-port="0" />
		<edge from-layer="397" from-port="1" to-layer="398" to-port="1" />
		<edge from-layer="398" from-port="2" to-layer="399" to-port="1" />
		<edge from-layer="399" from-port="2" to-layer="434" to-port="0" />
		<edge from-layer="399" from-port="2" to-layer="401" to-port="0" />
		<edge from-layer="400" from-port="0" to-layer="401" to-port="1" />
		<edge from-layer="401" from-port="2" to-layer="404" to-port="0" />
		<edge from-layer="402" from-port="0" to-layer="403" to-port="0" />
		<edge from-layer="403" from-port="1" to-layer="404" to-port="1" />
		<edge from-layer="404" from-port="2" to-layer="407" to-port="0" />
		<edge from-layer="405" from-port="0" 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="410" to-port="0" />
		<edge from-layer="408" from-port="0" to-layer="409" to-port="0" />
		<edge from-layer="409" from-port="1" to-layer="410" to-port="1" />
		<edge from-layer="410" from-port="2" to-layer="413" to-port="0" />
		<edge from-layer="411" from-port="0" to-layer="412" to-port="0" />
		<edge from-layer="412" from-port="1" to-layer="413" to-port="1" />
		<edge from-layer="413" from-port="2" to-layer="416" to-port="0" />
		<edge from-layer="414" from-port="0" to-layer="415" to-port="0" />
		<edge from-layer="415" from-port="1" to-layer="416" to-port="1" />
		<edge from-layer="416" from-port="2" to-layer="418" to-port="0" />
		<edge from-layer="417" from-port="0" to-layer="418" to-port="1" />
		<edge from-layer="418" from-port="2" to-layer="420" to-port="0" />
		<edge from-layer="419" from-port="0" to-layer="420" to-port="1" />
		<edge from-layer="420" from-port="2" to-layer="423" to-port="0" />
		<edge from-layer="421" from-port="0" to-layer="422" to-port="0" />
		<edge from-layer="422" from-port="1" to-layer="423" to-port="3" />
		<edge from-layer="423" from-port="5" to-layer="425" to-port="0" />
		<edge from-layer="424" from-port="0" to-layer="425" to-port="1" />
		<edge from-layer="425" from-port="2" to-layer="427" to-port="0" />
		<edge from-layer="426" from-port="0" to-layer="427" to-port="1" />
		<edge from-layer="427" from-port="2" to-layer="430" to-port="0" />
		<edge from-layer="428" from-port="0" to-layer="429" to-port="0" />
		<edge from-layer="429" from-port="1" to-layer="430" to-port="1" />
		<edge from-layer="430" from-port="2" to-layer="433" to-port="0" />
		<edge from-layer="431" from-port="0" to-layer="432" to-port="0" />
		<edge from-layer="432" from-port="1" to-layer="433" to-port="1" />
		<edge from-layer="433" from-port="2" to-layer="434" to-port="1" />
		<edge from-layer="434" from-port="2" to-layer="436" to-port="0" />
		<edge from-layer="434" from-port="2" to-layer="456" to-port="0" />
		<edge from-layer="435" from-port="0" to-layer="436" to-port="1" />
		<edge from-layer="436" from-port="2" to-layer="439" to-port="0" />
		<edge from-layer="437" from-port="0" to-layer="438" to-port="0" />
		<edge from-layer="438" from-port="1" to-layer="439" to-port="1" />
		<edge from-layer="439" from-port="2" to-layer="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="445" to-port="0" />
		<edge from-layer="443" from-port="0" to-layer="444" to-port="0" />
		<edge from-layer="444" from-port="1" to-layer="445" to-port="1" />
		<edge from-layer="445" from-port="2" to-layer="448" to-port="0" />
		<edge from-layer="446" from-port="0" to-layer="447" to-port="0" />
		<edge from-layer="447" from-port="1" to-layer="448" to-port="1" />
		<edge from-layer="448" from-port="2" to-layer="449" to-port="0" />
		<edge from-layer="449" from-port="1" to-layer="452" to-port="0" />
		<edge from-layer="450" from-port="0" to-layer="451" to-port="0" />
		<edge from-layer="451" from-port="1" to-layer="452" to-port="1" />
		<edge from-layer="452" from-port="2" to-layer="455" to-port="0" />
		<edge from-layer="453" from-port="0" to-layer="454" to-port="0" />
		<edge from-layer="454" from-port="1" to-layer="455" to-port="1" />
		<edge from-layer="455" from-port="2" to-layer="456" to-port="1" />
		<edge from-layer="456" from-port="2" to-layer="528" to-port="0" />
		<edge from-layer="456" from-port="2" to-layer="458" to-port="0" />
		<edge from-layer="457" from-port="0" to-layer="458" to-port="1" />
		<edge from-layer="458" from-port="2" to-layer="461" to-port="0" />
		<edge from-layer="459" from-port="0" to-layer="460" to-port="0" />
		<edge from-layer="460" from-port="1" to-layer="461" to-port="1" />
		<edge from-layer="461" from-port="2" to-layer="464" to-port="0" />
		<edge from-layer="462" from-port="0" to-layer="463" to-port="0" />
		<edge from-layer="463" from-port="1" to-layer="464" to-port="1" />
		<edge from-layer="464" from-port="2" to-layer="467" to-port="0" />
		<edge from-layer="464" from-port="2" to-layer="508" to-port="0" />
		<edge from-layer="464" from-port="2" to-layer="490" to-port="0" />
		<edge from-layer="465" from-port="0" to-layer="466" to-port="0" />
		<edge from-layer="466" from-port="1" to-layer="467" to-port="1" />
		<edge from-layer="467" from-port="2" to-layer="470" to-port="0" />
		<edge from-layer="468" from-port="0" to-layer="469" to-port="0" />
		<edge from-layer="469" from-port="1" to-layer="470" to-port="1" />
		<edge from-layer="470" from-port="2" to-layer="473" to-port="0" />
		<edge from-layer="471" from-port="0" to-layer="472" to-port="0" />
		<edge from-layer="472" from-port="1" to-layer="473" to-port="1" />
		<edge from-layer="473" from-port="2" to-layer="475" to-port="0" />
		<edge from-layer="474" from-port="0" to-layer="475" to-port="1" />
		<edge from-layer="475" from-port="2" to-layer="477" to-port="0" />
		<edge from-layer="476" from-port="0" to-layer="477" to-port="1" />
		<edge from-layer="477" from-port="2" to-layer="517" to-port="0" />
		<edge from-layer="478" from-port="0" to-layer="479" to-port="0" />
		<edge from-layer="479" from-port="1" to-layer="484" to-port="0" />
		<edge from-layer="480" from-port="0" to-layer="483" to-port="1" />
		<edge from-layer="481" from-port="0" to-layer="483" to-port="2" />
		<edge from-layer="482" from-port="0" to-layer="483" to-port="3" />
		<edge from-layer="483" from-port="4" to-layer="484" to-port="1" />
		<edge from-layer="484" from-port="2" to-layer="485" to-port="0" />
		<edge from-layer="485" from-port="1" to-layer="487" to-port="0" />
		<edge from-layer="486" from-port="0" to-layer="487" to-port="2" />
		<edge from-layer="487" from-port="3" to-layer="495" to-port="0" />
		<edge from-layer="488" from-port="0" to-layer="489" to-port="0" />
		<edge from-layer="489" from-port="1" to-layer="490" to-port="1" />
		<edge from-layer="490" from-port="2" to-layer="492" to-port="0" />
		<edge from-layer="491" from-port="0" to-layer="492" to-port="1" />
		<edge from-layer="492" from-port="2" to-layer="494" to-port="0" />
		<edge from-layer="493" from-port="0" to-layer="494" to-port="1" />
		<edge from-layer="494" from-port="2" to-layer="495" to-port="1" />
		<edge from-layer="495" from-port="2" to-layer="517" to-port="1" />
		<edge from-layer="495" from-port="2" to-layer="976" to-port="0" />
		<edge from-layer="496" from-port="0" to-layer="497" to-port="0" />
		<edge from-layer="497" from-port="1" to-layer="502" to-port="0" />
		<edge from-layer="498" from-port="0" to-layer="501" to-port="1" />
		<edge from-layer="499" from-port="0" to-layer="501" to-port="2" />
		<edge from-layer="500" from-port="0" to-layer="501" to-port="3" />
		<edge from-layer="501" from-port="4" to-layer="502" to-port="1" />
		<edge from-layer="502" from-port="2" to-layer="503" to-port="0" />
		<edge from-layer="503" from-port="1" to-layer="505" to-port="0" />
		<edge from-layer="504" from-port="0" to-layer="505" to-port="2" />
		<edge from-layer="505" from-port="3" to-layer="516" to-port="0" />
		<edge from-layer="506" from-port="0" to-layer="507" to-port="0" />
		<edge from-layer="507" from-port="1" to-layer="508" to-port="1" />
		<edge from-layer="508" from-port="2" to-layer="511" 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="511" to-port="1" />
		<edge from-layer="511" from-port="2" to-layer="513" to-port="0" />
		<edge from-layer="512" from-port="0" 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="1" />
		<edge from-layer="516" from-port="2" to-layer="517" to-port="2" />
		<edge from-layer="516" from-port="2" to-layer="977" to-port="0" />
		<edge from-layer="517" from-port="5" 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="524" to-port="0" />
		<edge from-layer="522" from-port="0" to-layer="523" to-port="0" />
		<edge from-layer="523" from-port="1" to-layer="524" to-port="1" />
		<edge from-layer="524" from-port="2" to-layer="527" to-port="0" />
		<edge from-layer="525" from-port="0" to-layer="526" to-port="0" />
		<edge from-layer="526" from-port="1" to-layer="527" to-port="1" />
		<edge from-layer="527" from-port="2" to-layer="528" to-port="1" />
		<edge from-layer="528" from-port="2" to-layer="563" to-port="0" />
		<edge from-layer="528" from-port="2" to-layer="530" to-port="0" />
		<edge from-layer="529" from-port="0" to-layer="530" to-port="1" />
		<edge from-layer="530" from-port="2" 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="536" to-port="0" />
		<edge from-layer="534" from-port="0" to-layer="535" to-port="0" />
		<edge from-layer="535" from-port="1" to-layer="536" to-port="1" />
		<edge from-layer="536" from-port="2" to-layer="539" to-port="0" />
		<edge from-layer="537" from-port="0" to-layer="538" to-port="0" />
		<edge from-layer="538" from-port="1" to-layer="539" to-port="1" />
		<edge from-layer="539" from-port="2" to-layer="542" to-port="0" />
		<edge from-layer="540" from-port="0" to-layer="541" to-port="0" />
		<edge from-layer="541" from-port="1" to-layer="542" to-port="1" />
		<edge from-layer="542" from-port="2" to-layer="545" to-port="0" />
		<edge from-layer="543" from-port="0" to-layer="544" to-port="0" />
		<edge from-layer="544" from-port="1" to-layer="545" to-port="1" />
		<edge from-layer="545" from-port="2" to-layer="547" to-port="0" />
		<edge from-layer="546" from-port="0" to-layer="547" to-port="1" />
		<edge from-layer="547" from-port="2" to-layer="549" to-port="0" />
		<edge from-layer="548" from-port="0" to-layer="549" to-port="1" />
		<edge from-layer="549" from-port="2" to-layer="552" to-port="0" />
		<edge from-layer="550" from-port="0" to-layer="551" to-port="0" />
		<edge from-layer="551" from-port="1" to-layer="552" to-port="3" />
		<edge from-layer="552" from-port="5" to-layer="554" to-port="0" />
		<edge from-layer="553" from-port="0" to-layer="554" to-port="1" />
		<edge from-layer="554" from-port="2" to-layer="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="559" to-port="0" />
		<edge from-layer="557" from-port="0" to-layer="558" to-port="0" />
		<edge from-layer="558" from-port="1" to-layer="559" to-port="1" />
		<edge from-layer="559" from-port="2" to-layer="562" to-port="0" />
		<edge from-layer="560" from-port="0" to-layer="561" to-port="0" />
		<edge from-layer="561" from-port="1" to-layer="562" to-port="1" />
		<edge from-layer="562" from-port="2" to-layer="563" to-port="1" />
		<edge from-layer="563" from-port="2" to-layer="585" to-port="0" />
		<edge from-layer="563" from-port="2" to-layer="565" to-port="0" />
		<edge from-layer="564" from-port="0" to-layer="565" to-port="1" />
		<edge from-layer="565" from-port="2" to-layer="568" to-port="0" />
		<edge from-layer="566" from-port="0" to-layer="567" to-port="0" />
		<edge from-layer="567" from-port="1" to-layer="568" to-port="1" />
		<edge from-layer="568" from-port="2" 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="574" to-port="0" />
		<edge from-layer="572" from-port="0" to-layer="573" to-port="0" />
		<edge from-layer="573" from-port="1" to-layer="574" to-port="1" />
		<edge from-layer="574" from-port="2" to-layer="577" to-port="0" />
		<edge from-layer="575" from-port="0" to-layer="576" to-port="0" />
		<edge from-layer="576" from-port="1" to-layer="577" to-port="1" />
		<edge from-layer="577" from-port="2" to-layer="578" to-port="0" />
		<edge from-layer="578" from-port="1" to-layer="581" to-port="0" />
		<edge from-layer="579" from-port="0" to-layer="580" to-port="0" />
		<edge from-layer="580" from-port="1" to-layer="581" to-port="1" />
		<edge from-layer="581" from-port="2" to-layer="584" to-port="0" />
		<edge from-layer="582" from-port="0" to-layer="583" to-port="0" />
		<edge from-layer="583" from-port="1" to-layer="584" to-port="1" />
		<edge from-layer="584" from-port="2" to-layer="585" to-port="1" />
		<edge from-layer="585" from-port="2" to-layer="657" to-port="0" />
		<edge from-layer="585" from-port="2" to-layer="587" to-port="0" />
		<edge from-layer="586" from-port="0" to-layer="587" to-port="1" />
		<edge from-layer="587" from-port="2" to-layer="590" to-port="0" />
		<edge from-layer="588" from-port="0" to-layer="589" to-port="0" />
		<edge from-layer="589" from-port="1" to-layer="590" to-port="1" />
		<edge from-layer="590" from-port="2" to-layer="593" to-port="0" />
		<edge from-layer="591" from-port="0" 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="619" to-port="0" />
		<edge from-layer="593" from-port="2" to-layer="596" to-port="0" />
		<edge from-layer="593" from-port="2" to-layer="637" to-port="0" />
		<edge from-layer="594" from-port="0" to-layer="595" to-port="0" />
		<edge from-layer="595" from-port="1" to-layer="596" to-port="1" />
		<edge from-layer="596" from-port="2" to-layer="599" to-port="0" />
		<edge from-layer="597" from-port="0" to-layer="598" to-port="0" />
		<edge from-layer="598" from-port="1" to-layer="599" to-port="1" />
		<edge from-layer="599" from-port="2" to-layer="602" to-port="0" />
		<edge from-layer="600" from-port="0" to-layer="601" to-port="0" />
		<edge from-layer="601" from-port="1" to-layer="602" to-port="1" />
		<edge from-layer="602" from-port="2" to-layer="604" to-port="0" />
		<edge from-layer="603" from-port="0" to-layer="604" to-port="1" />
		<edge from-layer="604" from-port="2" to-layer="606" to-port="0" />
		<edge from-layer="605" from-port="0" to-layer="606" to-port="1" />
		<edge from-layer="606" from-port="2" to-layer="646" to-port="0" />
		<edge from-layer="607" from-port="0" to-layer="608" to-port="0" />
		<edge from-layer="608" from-port="1" to-layer="613" to-port="0" />
		<edge from-layer="609" from-port="0" to-layer="612" to-port="1" />
		<edge from-layer="610" from-port="0" to-layer="612" to-port="2" />
		<edge from-layer="611" from-port="0" to-layer="612" to-port="3" />
		<edge from-layer="612" from-port="4" to-layer="613" to-port="1" />
		<edge from-layer="613" from-port="2" to-layer="614" to-port="0" />
		<edge from-layer="614" from-port="1" to-layer="616" to-port="0" />
		<edge from-layer="615" from-port="0" to-layer="616" to-port="2" />
		<edge from-layer="616" from-port="3" to-layer="624" to-port="0" />
		<edge from-layer="617" from-port="0" to-layer="618" to-port="0" />
		<edge from-layer="618" from-port="1" to-layer="619" to-port="1" />
		<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="624" to-port="1" />
		<edge from-layer="624" from-port="2" to-layer="978" to-port="0" />
		<edge from-layer="624" from-port="2" to-layer="646" to-port="1" />
		<edge from-layer="625" from-port="0" to-layer="626" to-port="0" />
		<edge from-layer="626" from-port="1" to-layer="631" to-port="0" />
		<edge from-layer="627" from-port="0" to-layer="630" to-port="1" />
		<edge from-layer="628" from-port="0" to-layer="630" to-port="2" />
		<edge from-layer="629" from-port="0" to-layer="630" to-port="3" />
		<edge from-layer="630" from-port="4" to-layer="631" to-port="1" />
		<edge from-layer="631" from-port="2" to-layer="632" to-port="0" />
		<edge from-layer="632" from-port="1" to-layer="634" to-port="0" />
		<edge from-layer="633" from-port="0" to-layer="634" to-port="2" />
		<edge from-layer="634" from-port="3" to-layer="645" to-port="0" />
		<edge from-layer="635" from-port="0" to-layer="636" to-port="0" />
		<edge from-layer="636" from-port="1" to-layer="637" to-port="1" />
		<edge from-layer="637" from-port="2" to-layer="640" 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="640" to-port="1" />
		<edge from-layer="640" from-port="2" to-layer="642" to-port="0" />
		<edge from-layer="641" from-port="0" to-layer="642" to-port="1" />
		<edge from-layer="642" from-port="2" to-layer="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="1" />
		<edge from-layer="645" from-port="2" to-layer="979" to-port="0" />
		<edge from-layer="645" from-port="2" to-layer="646" to-port="2" />
		<edge from-layer="646" from-port="5" 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="650" to-port="0" />
		<edge from-layer="649" from-port="0" to-layer="650" to-port="1" />
		<edge from-layer="650" from-port="2" to-layer="653" to-port="0" />
		<edge from-layer="651" from-port="0" to-layer="652" to-port="0" />
		<edge from-layer="652" from-port="1" to-layer="653" to-port="1" />
		<edge from-layer="653" from-port="2" to-layer="656" to-port="0" />
		<edge from-layer="654" from-port="0" to-layer="655" to-port="0" />
		<edge from-layer="655" from-port="1" to-layer="656" to-port="1" />
		<edge from-layer="656" from-port="2" to-layer="657" to-port="1" />
		<edge from-layer="657" from-port="2" to-layer="659" to-port="0" />
		<edge from-layer="657" from-port="2" to-layer="692" to-port="0" />
		<edge from-layer="658" from-port="0" to-layer="659" to-port="1" />
		<edge from-layer="659" from-port="2" to-layer="662" to-port="0" />
		<edge from-layer="660" from-port="0" to-layer="661" to-port="0" />
		<edge from-layer="661" from-port="1" to-layer="662" to-port="1" />
		<edge from-layer="662" from-port="2" to-layer="665" to-port="0" />
		<edge from-layer="663" from-port="0" to-layer="664" to-port="0" />
		<edge from-layer="664" from-port="1" to-layer="665" to-port="1" />
		<edge from-layer="665" from-port="2" to-layer="668" to-port="0" />
		<edge from-layer="666" from-port="0" to-layer="667" to-port="0" />
		<edge from-layer="667" from-port="1" to-layer="668" to-port="1" />
		<edge from-layer="668" from-port="2" to-layer="671" to-port="0" />
		<edge from-layer="669" from-port="0" to-layer="670" to-port="0" />
		<edge from-layer="670" from-port="1" to-layer="671" to-port="1" />
		<edge from-layer="671" from-port="2" to-layer="674" to-port="0" />
		<edge from-layer="672" from-port="0" to-layer="673" to-port="0" />
		<edge from-layer="673" from-port="1" to-layer="674" to-port="1" />
		<edge from-layer="674" from-port="2" to-layer="676" to-port="0" />
		<edge from-layer="675" from-port="0" to-layer="676" to-port="1" />
		<edge from-layer="676" from-port="2" to-layer="678" to-port="0" />
		<edge from-layer="677" from-port="0" to-layer="678" to-port="1" />
		<edge from-layer="678" from-port="2" to-layer="681" to-port="0" />
		<edge from-layer="679" from-port="0" to-layer="680" to-port="0" />
		<edge from-layer="680" from-port="1" to-layer="681" to-port="3" />
		<edge from-layer="681" from-port="5" to-layer="683" to-port="0" />
		<edge from-layer="682" from-port="0" to-layer="683" to-port="1" />
		<edge from-layer="683" from-port="2" to-layer="685" to-port="0" />
		<edge from-layer="684" from-port="0" to-layer="685" to-port="1" />
		<edge from-layer="685" from-port="2" to-layer="688" to-port="0" />
		<edge from-layer="686" from-port="0" to-layer="687" to-port="0" />
		<edge from-layer="687" from-port="1" to-layer="688" to-port="1" />
		<edge from-layer="688" from-port="2" to-layer="691" 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="691" to-port="1" />
		<edge from-layer="691" from-port="2" to-layer="692" to-port="1" />
		<edge from-layer="692" from-port="2" to-layer="714" to-port="0" />
		<edge from-layer="692" from-port="2" to-layer="694" to-port="0" />
		<edge from-layer="693" from-port="0" to-layer="694" to-port="1" />
		<edge from-layer="694" from-port="2" to-layer="697" to-port="0" />
		<edge from-layer="695" from-port="0" 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="700" to-port="0" />
		<edge from-layer="698" from-port="0" to-layer="699" to-port="0" />
		<edge from-layer="699" from-port="1" to-layer="700" to-port="1" />
		<edge from-layer="700" from-port="2" to-layer="703" to-port="0" />
		<edge from-layer="701" from-port="0" to-layer="702" to-port="0" />
		<edge from-layer="702" from-port="1" to-layer="703" to-port="1" />
		<edge from-layer="703" from-port="2" to-layer="706" to-port="0" />
		<edge from-layer="704" from-port="0" to-layer="705" to-port="0" />
		<edge from-layer="705" from-port="1" to-layer="706" to-port="1" />
		<edge from-layer="706" from-port="2" to-layer="707" to-port="0" />
		<edge from-layer="707" from-port="1" to-layer="710" to-port="0" />
		<edge from-layer="708" from-port="0" to-layer="709" to-port="0" />
		<edge from-layer="709" from-port="1" to-layer="710" to-port="1" />
		<edge from-layer="710" from-port="2" to-layer="713" 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="713" to-port="1" />
		<edge from-layer="713" from-port="2" to-layer="714" to-port="1" />
		<edge from-layer="714" from-port="2" to-layer="786" to-port="0" />
		<edge from-layer="714" from-port="2" to-layer="716" to-port="0" />
		<edge from-layer="715" from-port="0" to-layer="716" to-port="1" />
		<edge from-layer="716" from-port="2" to-layer="719" to-port="0" />
		<edge from-layer="717" from-port="0" 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="722" to-port="0" />
		<edge from-layer="720" from-port="0" to-layer="721" to-port="0" />
		<edge from-layer="721" from-port="1" to-layer="722" to-port="1" />
		<edge from-layer="722" from-port="2" to-layer="748" to-port="0" />
		<edge from-layer="722" from-port="2" to-layer="766" to-port="0" />
		<edge from-layer="722" from-port="2" to-layer="725" to-port="0" />
		<edge from-layer="723" from-port="0" to-layer="724" to-port="0" />
		<edge from-layer="724" from-port="1" to-layer="725" to-port="1" />
		<edge from-layer="725" from-port="2" to-layer="728" to-port="0" />
		<edge from-layer="726" from-port="0" to-layer="727" to-port="0" />
		<edge from-layer="727" from-port="1" to-layer="728" to-port="1" />
		<edge from-layer="728" from-port="2" to-layer="731" 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="731" to-port="1" />
		<edge from-layer="731" from-port="2" to-layer="733" to-port="0" />
		<edge from-layer="732" from-port="0" 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="775" to-port="0" />
		<edge from-layer="736" from-port="0" to-layer="737" to-port="0" />
		<edge from-layer="737" from-port="1" to-layer="742" to-port="0" />
		<edge from-layer="738" from-port="0" to-layer="741" to-port="1" />
		<edge from-layer="739" from-port="0" to-layer="741" to-port="2" />
		<edge from-layer="740" from-port="0" to-layer="741" to-port="3" />
		<edge from-layer="741" from-port="4" to-layer="742" to-port="1" />
		<edge from-layer="742" from-port="2" to-layer="743" to-port="0" />
		<edge from-layer="743" from-port="1" to-layer="745" to-port="0" />
		<edge from-layer="744" from-port="0" to-layer="745" to-port="2" />
		<edge from-layer="745" from-port="3" to-layer="753" to-port="0" />
		<edge from-layer="746" from-port="0" to-layer="747" to-port="0" />
		<edge from-layer="747" from-port="1" to-layer="748" to-port="1" />
		<edge from-layer="748" from-port="2" to-layer="750" to-port="0" />
		<edge from-layer="749" from-port="0" to-layer="750" to-port="1" />
		<edge from-layer="750" from-port="2" to-layer="752" to-port="0" />
		<edge from-layer="751" from-port="0" to-layer="752" to-port="1" />
		<edge from-layer="752" from-port="2" to-layer="753" to-port="1" />
		<edge from-layer="753" from-port="2" to-layer="775" to-port="1" />
		<edge from-layer="753" from-port="2" to-layer="980" 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="760" to-port="0" />
		<edge from-layer="756" from-port="0" to-layer="759" to-port="1" />
		<edge from-layer="757" from-port="0" to-layer="759" to-port="2" />
		<edge from-layer="758" from-port="0" to-layer="759" to-port="3" />
		<edge from-layer="759" from-port="4" to-layer="760" to-port="1" />
		<edge from-layer="760" from-port="2" to-layer="761" to-port="0" />
		<edge from-layer="761" from-port="1" to-layer="763" to-port="0" />
		<edge from-layer="762" from-port="0" to-layer="763" to-port="2" />
		<edge from-layer="763" from-port="3" to-layer="774" to-port="0" />
		<edge from-layer="764" from-port="0" to-layer="765" to-port="0" />
		<edge from-layer="765" from-port="1" to-layer="766" to-port="1" />
		<edge from-layer="766" from-port="2" to-layer="769" to-port="0" />
		<edge from-layer="767" from-port="0" to-layer="768" to-port="0" />
		<edge from-layer="768" from-port="1" to-layer="769" to-port="1" />
		<edge from-layer="769" from-port="2" to-layer="771" to-port="0" />
		<edge from-layer="770" from-port="0" to-layer="771" to-port="1" />
		<edge from-layer="771" from-port="2" to-layer="773" to-port="0" />
		<edge from-layer="772" from-port="0" to-layer="773" to-port="1" />
		<edge from-layer="773" from-port="2" to-layer="774" to-port="1" />
		<edge from-layer="774" from-port="2" to-layer="981" to-port="0" />
		<edge from-layer="774" from-port="2" to-layer="775" to-port="2" />
		<edge from-layer="775" from-port="5" to-layer="777" to-port="0" />
		<edge from-layer="776" from-port="0" to-layer="777" to-port="1" />
		<edge from-layer="777" from-port="2" to-layer="779" to-port="0" />
		<edge from-layer="778" from-port="0" to-layer="779" to-port="1" />
		<edge from-layer="779" from-port="2" to-layer="782" to-port="0" />
		<edge from-layer="780" from-port="0" to-layer="781" to-port="0" />
		<edge from-layer="781" from-port="1" to-layer="782" to-port="1" />
		<edge from-layer="782" from-port="2" to-layer="785" to-port="0" />
		<edge from-layer="783" from-port="0" to-layer="784" to-port="0" />
		<edge from-layer="784" from-port="1" to-layer="785" to-port="1" />
		<edge from-layer="785" from-port="2" to-layer="786" to-port="1" />
		<edge from-layer="786" from-port="2" to-layer="788" to-port="0" />
		<edge from-layer="786" from-port="2" to-layer="821" 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="791" to-port="0" />
		<edge from-layer="789" from-port="0" to-layer="790" to-port="0" />
		<edge from-layer="790" from-port="1" to-layer="791" to-port="1" />
		<edge from-layer="791" from-port="2" to-layer="794" to-port="0" />
		<edge from-layer="792" from-port="0" to-layer="793" to-port="0" />
		<edge from-layer="793" from-port="1" to-layer="794" to-port="1" />
		<edge from-layer="794" from-port="2" to-layer="797" to-port="0" />
		<edge from-layer="795" from-port="0" to-layer="796" to-port="0" />
		<edge from-layer="796" from-port="1" to-layer="797" to-port="1" />
		<edge from-layer="797" from-port="2" to-layer="800" to-port="0" />
		<edge from-layer="798" from-port="0" to-layer="799" to-port="0" />
		<edge from-layer="799" from-port="1" to-layer="800" to-port="1" />
		<edge from-layer="800" from-port="2" to-layer="803" to-port="0" />
		<edge from-layer="801" from-port="0" to-layer="802" to-port="0" />
		<edge from-layer="802" from-port="1" to-layer="803" to-port="1" />
		<edge from-layer="803" from-port="2" to-layer="805" to-port="0" />
		<edge from-layer="804" from-port="0" to-layer="805" to-port="1" />
		<edge from-layer="805" from-port="2" to-layer="807" to-port="0" />
		<edge from-layer="806" from-port="0" to-layer="807" to-port="1" />
		<edge from-layer="807" from-port="2" to-layer="810" to-port="0" />
		<edge from-layer="808" from-port="0" to-layer="809" to-port="0" />
		<edge from-layer="809" from-port="1" to-layer="810" to-port="3" />
		<edge from-layer="810" from-port="5" to-layer="812" to-port="0" />
		<edge from-layer="811" from-port="0" to-layer="812" to-port="1" />
		<edge from-layer="812" from-port="2" to-layer="814" to-port="0" />
		<edge from-layer="813" from-port="0" to-layer="814" to-port="1" />
		<edge from-layer="814" from-port="2" to-layer="817" to-port="0" />
		<edge from-layer="815" from-port="0" to-layer="816" to-port="0" />
		<edge from-layer="816" from-port="1" to-layer="817" to-port="1" />
		<edge from-layer="817" from-port="2" to-layer="820" to-port="0" />
		<edge from-layer="818" from-port="0" to-layer="819" to-port="0" />
		<edge from-layer="819" from-port="1" to-layer="820" to-port="1" />
		<edge from-layer="820" from-port="2" to-layer="821" to-port="1" />
		<edge from-layer="821" from-port="2" to-layer="843" to-port="0" />
		<edge from-layer="821" from-port="2" to-layer="823" to-port="0" />
		<edge from-layer="822" from-port="0" to-layer="823" to-port="1" />
		<edge from-layer="823" from-port="2" to-layer="826" to-port="0" />
		<edge from-layer="824" from-port="0" to-layer="825" to-port="0" />
		<edge from-layer="825" from-port="1" to-layer="826" to-port="1" />
		<edge from-layer="826" from-port="2" to-layer="829" to-port="0" />
		<edge from-layer="827" from-port="0" to-layer="828" to-port="0" />
		<edge from-layer="828" from-port="1" to-layer="829" to-port="1" />
		<edge from-layer="829" from-port="2" to-layer="832" to-port="0" />
		<edge from-layer="830" from-port="0" to-layer="831" to-port="0" />
		<edge from-layer="831" from-port="1" to-layer="832" to-port="1" />
		<edge from-layer="832" from-port="2" to-layer="835" to-port="0" />
		<edge from-layer="833" from-port="0" to-layer="834" to-port="0" />
		<edge from-layer="834" from-port="1" to-layer="835" to-port="1" />
		<edge from-layer="835" from-port="2" to-layer="836" to-port="0" />
		<edge from-layer="836" from-port="1" to-layer="839" to-port="0" />
		<edge from-layer="837" from-port="0" to-layer="838" to-port="0" />
		<edge from-layer="838" from-port="1" to-layer="839" to-port="1" />
		<edge from-layer="839" from-port="2" to-layer="842" to-port="0" />
		<edge from-layer="840" from-port="0" to-layer="841" to-port="0" />
		<edge from-layer="841" from-port="1" to-layer="842" to-port="1" />
		<edge from-layer="842" from-port="2" to-layer="843" to-port="1" />
		<edge from-layer="843" from-port="2" to-layer="905" to-port="0" />
		<edge from-layer="843" from-port="2" to-layer="845" to-port="0" />
		<edge from-layer="844" from-port="0" to-layer="845" to-port="1" />
		<edge from-layer="845" from-port="2" to-layer="848" to-port="0" />
		<edge from-layer="846" from-port="0" to-layer="847" to-port="0" />
		<edge from-layer="847" from-port="1" to-layer="848" to-port="1" />
		<edge from-layer="848" from-port="2" to-layer="851" to-port="0" />
		<edge from-layer="849" from-port="0" to-layer="850" to-port="0" />
		<edge from-layer="850" from-port="1" to-layer="851" to-port="1" />
		<edge from-layer="851" from-port="2" to-layer="875" to-port="0" />
		<edge from-layer="851" from-port="2" to-layer="854" to-port="0" />
		<edge from-layer="851" from-port="2" to-layer="883" to-port="0" />
		<edge from-layer="852" from-port="0" to-layer="853" to-port="0" />
		<edge from-layer="853" from-port="1" to-layer="854" to-port="1" />
		<edge from-layer="854" from-port="2" to-layer="857" to-port="0" />
		<edge from-layer="855" from-port="0" to-layer="856" to-port="0" />
		<edge from-layer="856" from-port="1" to-layer="857" to-port="1" />
		<edge from-layer="857" from-port="2" to-layer="859" to-port="0" />
		<edge from-layer="858" from-port="0" to-layer="859" to-port="1" />
		<edge from-layer="859" from-port="2" to-layer="861" to-port="0" />
		<edge from-layer="860" from-port="0" to-layer="861" to-port="1" />
		<edge from-layer="861" from-port="2" to-layer="862" to-port="1" />
		<edge from-layer="862" from-port="2" to-layer="983" to-port="0" />
		<edge from-layer="862" from-port="2" to-layer="894" to-port="2" />
		<edge from-layer="863" from-port="0" to-layer="864" to-port="0" />
		<edge from-layer="864" from-port="1" to-layer="869" to-port="0" />
		<edge from-layer="865" from-port="0" to-layer="868" to-port="1" />
		<edge from-layer="866" from-port="0" to-layer="868" to-port="2" />
		<edge from-layer="867" from-port="0" to-layer="868" to-port="3" />
		<edge from-layer="868" from-port="4" to-layer="869" to-port="1" />
		<edge from-layer="869" from-port="2" to-layer="870" to-port="0" />
		<edge from-layer="870" from-port="1" to-layer="872" to-port="0" />
		<edge from-layer="871" from-port="0" to-layer="872" to-port="2" />
		<edge from-layer="872" from-port="3" to-layer="880" to-port="0" />
		<edge from-layer="873" from-port="0" to-layer="874" to-port="0" />
		<edge from-layer="874" from-port="1" to-layer="875" to-port="1" />
		<edge from-layer="875" from-port="2" to-layer="877" to-port="0" />
		<edge from-layer="876" from-port="0" to-layer="877" to-port="1" />
		<edge from-layer="877" from-port="2" to-layer="879" to-port="0" />
		<edge from-layer="878" from-port="0" to-layer="879" to-port="1" />
		<edge from-layer="879" from-port="2" to-layer="880" to-port="1" />
		<edge from-layer="880" from-port="2" to-layer="982" to-port="0" />
		<edge from-layer="880" from-port="2" to-layer="894" to-port="1" />
		<edge from-layer="881" from-port="0" to-layer="882" to-port="0" />
		<edge from-layer="882" from-port="1" to-layer="883" to-port="1" />
		<edge from-layer="883" from-port="2" to-layer="886" to-port="0" />
		<edge from-layer="884" from-port="0" to-layer="885" to-port="0" />
		<edge from-layer="885" from-port="1" to-layer="886" to-port="1" />
		<edge from-layer="886" from-port="2" to-layer="889" to-port="0" />
		<edge from-layer="887" from-port="0" to-layer="888" to-port="0" />
		<edge from-layer="888" from-port="1" to-layer="889" to-port="1" />
		<edge from-layer="889" from-port="2" to-layer="891" to-port="0" />
		<edge from-layer="890" from-port="0" to-layer="891" to-port="1" />
		<edge from-layer="891" from-port="2" to-layer="893" to-port="0" />
		<edge from-layer="892" from-port="0" to-layer="893" to-port="1" />
		<edge from-layer="893" from-port="2" to-layer="894" to-port="0" />
		<edge from-layer="894" from-port="5" to-layer="896" to-port="0" />
		<edge from-layer="895" from-port="0" to-layer="896" to-port="1" />
		<edge from-layer="896" from-port="2" to-layer="898" to-port="0" />
		<edge from-layer="897" from-port="0" to-layer="898" to-port="1" />
		<edge from-layer="898" from-port="2" to-layer="901" to-port="0" />
		<edge from-layer="899" from-port="0" to-layer="900" to-port="0" />
		<edge from-layer="900" from-port="1" to-layer="901" to-port="1" />
		<edge from-layer="901" from-port="2" to-layer="904" to-port="0" />
		<edge from-layer="902" from-port="0" to-layer="903" to-port="0" />
		<edge from-layer="903" from-port="1" to-layer="904" to-port="1" />
		<edge from-layer="904" from-port="2" to-layer="905" to-port="1" />
		<edge from-layer="905" from-port="2" to-layer="907" to-port="0" />
		<edge from-layer="905" from-port="2" to-layer="940" to-port="0" />
		<edge from-layer="906" from-port="0" to-layer="907" to-port="1" />
		<edge from-layer="907" from-port="2" to-layer="910" to-port="0" />
		<edge from-layer="908" from-port="0" to-layer="909" to-port="0" />
		<edge from-layer="909" from-port="1" to-layer="910" to-port="1" />
		<edge from-layer="910" from-port="2" to-layer="913" to-port="0" />
		<edge from-layer="911" from-port="0" to-layer="912" to-port="0" />
		<edge from-layer="912" from-port="1" to-layer="913" to-port="1" />
		<edge from-layer="913" from-port="2" to-layer="916" to-port="0" />
		<edge from-layer="914" from-port="0" to-layer="915" to-port="0" />
		<edge from-layer="915" from-port="1" to-layer="916" to-port="1" />
		<edge from-layer="916" from-port="2" to-layer="919" to-port="0" />
		<edge from-layer="917" from-port="0" to-layer="918" to-port="0" />
		<edge from-layer="918" from-port="1" to-layer="919" to-port="1" />
		<edge from-layer="919" from-port="2" to-layer="922" to-port="0" />
		<edge from-layer="920" from-port="0" to-layer="921" to-port="0" />
		<edge from-layer="921" from-port="1" to-layer="922" to-port="1" />
		<edge from-layer="922" from-port="2" to-layer="924" to-port="0" />
		<edge from-layer="923" from-port="0" to-layer="924" to-port="1" />
		<edge from-layer="924" from-port="2" to-layer="926" to-port="0" />
		<edge from-layer="925" from-port="0" to-layer="926" to-port="1" />
		<edge from-layer="926" from-port="2" to-layer="929" to-port="0" />
		<edge from-layer="927" from-port="0" to-layer="928" to-port="0" />
		<edge from-layer="928" from-port="1" to-layer="929" to-port="3" />
		<edge from-layer="929" from-port="5" to-layer="931" to-port="0" />
		<edge from-layer="930" from-port="0" to-layer="931" to-port="1" />
		<edge from-layer="931" from-port="2" to-layer="933" to-port="0" />
		<edge from-layer="932" from-port="0" to-layer="933" to-port="1" />
		<edge from-layer="933" from-port="2" to-layer="936" to-port="0" />
		<edge from-layer="934" from-port="0" to-layer="935" to-port="0" />
		<edge from-layer="935" from-port="1" to-layer="936" to-port="1" />
		<edge from-layer="936" from-port="2" to-layer="939" to-port="0" />
		<edge from-layer="937" from-port="0" to-layer="938" to-port="0" />
		<edge from-layer="938" from-port="1" to-layer="939" to-port="1" />
		<edge from-layer="939" from-port="2" to-layer="940" to-port="1" />
		<edge from-layer="940" from-port="2" to-layer="962" to-port="0" />
		<edge from-layer="940" from-port="2" to-layer="942" to-port="0" />
		<edge from-layer="941" from-port="0" to-layer="942" to-port="1" />
		<edge from-layer="942" from-port="2" to-layer="945" to-port="0" />
		<edge from-layer="943" from-port="0" to-layer="944" to-port="0" />
		<edge from-layer="944" from-port="1" to-layer="945" to-port="1" />
		<edge from-layer="945" from-port="2" to-layer="948" to-port="0" />
		<edge from-layer="946" from-port="0" to-layer="947" to-port="0" />
		<edge from-layer="947" from-port="1" to-layer="948" to-port="1" />
		<edge from-layer="948" from-port="2" to-layer="951" to-port="0" />
		<edge from-layer="949" from-port="0" to-layer="950" to-port="0" />
		<edge from-layer="950" from-port="1" to-layer="951" to-port="1" />
		<edge from-layer="951" from-port="2" to-layer="954" to-port="0" />
		<edge from-layer="952" from-port="0" to-layer="953" to-port="0" />
		<edge from-layer="953" from-port="1" to-layer="954" to-port="1" />
		<edge from-layer="954" from-port="2" to-layer="955" to-port="0" />
		<edge from-layer="955" from-port="1" to-layer="958" to-port="0" />
		<edge from-layer="956" from-port="0" to-layer="957" to-port="0" />
		<edge from-layer="957" from-port="1" to-layer="958" to-port="1" />
		<edge from-layer="958" from-port="2" to-layer="961" to-port="0" />
		<edge from-layer="959" from-port="0" to-layer="960" to-port="0" />
		<edge from-layer="960" from-port="1" to-layer="961" to-port="1" />
		<edge from-layer="961" from-port="2" to-layer="962" to-port="1" />
		<edge from-layer="962" from-port="2" to-layer="964" to-port="0" />
		<edge from-layer="963" from-port="0" to-layer="964" to-port="1" />
		<edge from-layer="964" from-port="2" to-layer="967" to-port="0" />
		<edge from-layer="965" from-port="0" to-layer="966" to-port="0" />
		<edge from-layer="966" from-port="1" to-layer="967" to-port="1" />
		<edge from-layer="967" from-port="2" to-layer="970" to-port="0" />
		<edge from-layer="968" from-port="0" to-layer="969" to-port="0" />
		<edge from-layer="969" from-port="1" to-layer="970" to-port="1" />
		<edge from-layer="970" from-port="2" to-layer="971" to-port="0" />
		<edge from-layer="971" from-port="2" to-layer="996" 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>
		<optimum>
			<optimum_intel_version value="1.27.0" />
			<optimum_version value="2.1.0" />
			<pytorch_version value="2.10.0+cpu" />
			<transformers_version value="4.57.6" />
		</optimum>
		<runtime_options>
			<ACTIVATIONS_SCALE_FACTOR value="8.0" />
			<KV_CACHE_PRECISION value="f16" />
		</runtime_options>
	</rt_info>
</net>