openvino_encoder_model.xml

<?xml version="1.0"?>
<net name="Model0" version="11">
	<layers>
		<layer id="0" name="input_features" type="Parameter" version="opset1">
			<data shape="?,?,3000" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="input_features">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="self.conv1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 80, 3" offset="0" size="122880" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="Convert_223723" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="self.conv1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1, 1" offset="122880" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Convert_223726" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="self.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="self.conv1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1, 1" offset="123392" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="self.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="self.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="__module.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
			<data strides="1" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="__module.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
			<data element_type="f32" shape="1, 512, 1" offset="124416" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="__module.conv1/aten::_convolution/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="59">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>3000</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="20,input.1">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="self.conv2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512, 3" offset="126464" size="786432" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="Convert_97048" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="self.conv2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1, 1" offset="912896" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="Convert_97051" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="self.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="18" name="self.conv2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1, 1" offset="913408" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="self.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="20" name="self.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="21" name="__module.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
			<data strides="2" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="__module.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
			<data element_type="f32" shape="1, 512, 1" offset="914432" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="__module.conv2/aten::_convolution/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="71">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="24" name="aten::gelu/Gelu_1" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="23,inputs_embeds.1">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="Constant_118" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="916480" size="24" />
			<output>
				<port id="0" precision="I64" names="27">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="26" name="aten::permute/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>512</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="28,inputs_embeds">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="27" name="Constant_6254" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1500, 512" offset="916504" size="3072000" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="37,input.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="29" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="31" name="Constant_6255" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="3988508" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="Constant_6256" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="3990556" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="100,hidden_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="self.layers.0.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="3992604" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="Convert_112249" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="self.layers.0.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="4254748" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="Convert_112252" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="self.layers.0.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="self.layers.0.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="4255260" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="self.layers.0.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="self.layers.0.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="Constant_6257" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="4256284" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="Multiply_6162" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="Constant_6258" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="4256288" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="__module.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="110,query_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="Constant_6429" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="__module.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="112,query_states.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="__module.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="__module.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="113">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="self.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="4258384" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="Convert_107182" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="self.layers.0.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="4520528" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="Convert_107185" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="self.layers.0.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="self.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="4521040" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="self.layers.0.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="self.layers.0.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="60" name="__module.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="116">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="Constant_6430" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="__module.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="118,key_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="__module.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="__module.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="124">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="self.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="4522064" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Convert_102115" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="self.layers.0.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="4784208" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="Convert_102118" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="self.layers.0.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="70" name="self.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="4784720" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="self.layers.0.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="self.layers.0.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="73" name="__module.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="Constant_6259" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="4785744" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="__module.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="121">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="Constant_6431" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="__module.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="123,value_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="__module.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.layers.0.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="126">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="__module.layers.0.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787792" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="81" name="__module.layers.0.self_attn/aten::scaled_dot_product_attention/ConvertLike_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="82" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="128,attn_output.1">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="__module.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="129">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="Constant_6432" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="4787800" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="__module.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="132">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="self.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="4787824" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="Convert_117316" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="self.layers.0.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="5049968" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="Convert_117319" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="self.layers.0.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="self.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="5050480" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="self.layers.0.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="self.layers.0.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="__module.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="Constant_6260" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="5051504" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="__module.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="136,input.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="__module.layers.0/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="138,input.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="__module.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="Constant_6261" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="5053552" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="Constant_6262" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="5055600" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="__module.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="142,input.15">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="self.layers.0.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 512" offset="5057648" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="Convert_36244" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="self.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 1" offset="6106224" size="2048" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="Convert_36247" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="self.layers.0.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="self.layers.0.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 1" offset="6108272" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="self.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="self.layers.0.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="__module.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="Constant_6263" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 2048" offset="6112368" size="8192" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="__module.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="145,input.17">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="__module.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="146,input.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="self.layers.0.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 2048" offset="6120560" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="Convert_41311" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="self.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="7169136" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="Convert_41314" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="self.layers.0.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="self.layers.0.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="7169648" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="self.layers.0.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="124" name="self.layers.0.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="__module.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="Constant_6264" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="7170672" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="__module.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="150,input.23">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="__module.layers.0/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="152,input.25">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="Constant_6265" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="7172720" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="Constant_6266" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="7174768" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="177,hidden_states.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="135" name="self.layers.1.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="7176816" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="Convert_132517" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="self.layers.1.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="7438960" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="Convert_132520" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="self.layers.1.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="self.layers.1.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="7439472" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="self.layers.1.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="self.layers.1.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="Constant_6267" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="4256284" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="Multiply_6166" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="Constant_6268" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="7440496" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="__module.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="187,query_states.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="Constant_6433" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="__module.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="189,query_states.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="__module.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="__module.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="190">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="self.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="7442544" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="Convert_127450" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="self.layers.1.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="7704688" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="Convert_127453" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="self.layers.1.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="self.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="7705200" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="self.layers.1.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="159" name="self.layers.1.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="__module.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="193">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="Constant_6434" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="__module.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="195,key_states.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="__module.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="__module.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</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>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="self.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="7706224" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="Convert_122383" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="self.layers.1.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="7968368" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="168" name="Convert_122386" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="self.layers.1.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="self.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="7968880" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="171" name="self.layers.1.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="self.layers.1.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="__module.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="Constant_6269" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="7969904" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="__module.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="198">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="Constant_6435" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="177" name="__module.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="200,value_states.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="__module.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="__module.layers.1.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="203">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="180" name="__module.layers.1.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787792" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="181" name="__module.layers.1.self_attn/aten::scaled_dot_product_attention/ConvertLike_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="182" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="205,attn_output.5">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="__module.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="206">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="Constant_6436" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="4787800" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="__module.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="209">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="self.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="7971952" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="Convert_137584" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="self.layers.1.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="8234096" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="Convert_137587" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="self.layers.1.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="self.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="8234608" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="193" name="self.layers.1.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="self.layers.1.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="__module.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="196" name="Constant_6270" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="8235632" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="213,input.29">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="198" name="__module.layers.1/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="215,input.31">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="__module.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="201" name="Constant_6271" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="8237680" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="203" name="Constant_6272" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="8239728" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="__module.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="219,input.33">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="self.layers.1.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 512" offset="8241776" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="Convert_46378" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="self.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 1" offset="9290352" size="2048" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="Convert_46381" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="self.layers.1.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="self.layers.1.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 1" offset="9292400" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="self.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="self.layers.1.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="__module.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="214" name="Constant_6273" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 2048" offset="9296496" size="8192" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="__module.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="222,input.35">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="__module.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="223,input.37">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="217" name="self.layers.1.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 2048" offset="9304688" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="218" name="Convert_51445" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="219" name="self.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="10353264" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="Convert_51448" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="221" name="self.layers.1.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="222" name="self.layers.1.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="10353776" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="self.layers.1.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="self.layers.1.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="__module.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="Constant_6274" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="10354800" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="__module.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="227,input.41">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="__module.layers.1/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="229,input.43">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="230" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="Constant_6275" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="10356848" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="233" name="Constant_6276" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="10358896" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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,hidden_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="235" name="self.layers.2.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="10360944" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="236" name="Convert_152785" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="self.layers.2.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="10623088" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="Convert_152788" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="239" name="self.layers.2.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="self.layers.2.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="10623600" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="self.layers.2.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="242" name="self.layers.2.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="244" name="Constant_6277" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="4256284" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="Multiply_6170" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="Constant_6278" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="10624624" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="247" name="__module.layers.2.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="264,query_states.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="248" name="Constant_6437" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="249" name="__module.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="266,query_states.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="250" name="__module.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="__module.layers.2.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="267">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="252" name="self.layers.2.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="10626672" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="253" name="Convert_147718" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="254" name="self.layers.2.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="10888816" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="Convert_147721" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="256" name="self.layers.2.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="257" name="self.layers.2.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="10889328" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="258" name="self.layers.2.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="259" name="self.layers.2.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="__module.layers.2.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="270">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="Constant_6438" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="__module.layers.2.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="272,key_states.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="__module.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="__module.layers.2.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="278">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="self.layers.2.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="10890352" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="Convert_142651" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="self.layers.2.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="11152496" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="Convert_142654" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="269" name="self.layers.2.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="self.layers.2.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="11153008" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="self.layers.2.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="272" name="self.layers.2.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="__module.layers.2.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="Constant_6279" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="11154032" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="__module.layers.2.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="275">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="Constant_6439" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="__module.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="277,value_states.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="__module.layers.2.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="__module.layers.2.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="280">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="__module.layers.2.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787792" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="281" name="__module.layers.2.self_attn/aten::scaled_dot_product_attention/ConvertLike_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="282" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="282,attn_output.9">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="__module.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="283">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="Constant_6440" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="4787800" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="__module.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="286">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="287" name="self.layers.2.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="11156080" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="Convert_157852" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="289" name="self.layers.2.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="11418224" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="Convert_157855" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="self.layers.2.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="self.layers.2.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="11418736" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="self.layers.2.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="self.layers.2.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="__module.layers.2.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="Constant_6280" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="11419760" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="__module.layers.2.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="290,input.47">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="__module.layers.2/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="292,input.49">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="__module.layers.2.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="301" name="Constant_6281" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="11421808" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="Constant_6282" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="11423856" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="__module.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="296,input.51">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="305" name="self.layers.2.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 512" offset="11425904" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="Convert_56512" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="self.layers.2.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 1" offset="12474480" size="2048" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="Convert_56515" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="self.layers.2.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="self.layers.2.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 1" offset="12476528" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="self.layers.2.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="self.layers.2.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="313" name="__module.layers.2.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="Constant_6283" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 2048" offset="12480624" size="8192" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="__module.layers.2.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="299,input.53">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="316" name="__module.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="300,input.55">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="self.layers.2.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 2048" offset="12488816" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="Convert_61579" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="319" name="self.layers.2.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="13537392" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="320" name="Convert_61582" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="self.layers.2.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="self.layers.2.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="13537904" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="323" name="self.layers.2.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="324" name="self.layers.2.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="325" name="__module.layers.2.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="326" name="Constant_6284" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="13538928" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="327" name="__module.layers.2.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="304,input.59">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="328" name="__module.layers.2/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="306,input.61">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="329" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="330" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="331" name="Constant_6285" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="13540976" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="332" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="333" name="Constant_6286" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="13543024" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="331,hidden_states.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="335" name="self.layers.3.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="13545072" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="Convert_173053" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="self.layers.3.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="13807216" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="338" name="Convert_173056" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="self.layers.3.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="self.layers.3.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="13807728" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="self.layers.3.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="self.layers.3.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="344" name="Constant_6287" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="4256284" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="345" name="Multiply_6174" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="346" name="Constant_6288" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="13808752" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="__module.layers.3.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="341,query_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="348" name="Constant_6441" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="__module.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="343,query_states.15">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="350" name="__module.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="351" name="__module.layers.3.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="344">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="self.layers.3.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="13810800" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="353" name="Convert_167986" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="self.layers.3.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="14072944" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="355" name="Convert_167989" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="self.layers.3.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="self.layers.3.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="14073456" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="358" name="self.layers.3.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="self.layers.3.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="__module.layers.3.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="347">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="361" name="Constant_6442" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="362" name="__module.layers.3.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="349,key_states.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="363" name="__module.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="__module.layers.3.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="355">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="365" name="self.layers.3.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="14074480" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="366" name="Convert_162919" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="367" name="self.layers.3.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="14336624" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="368" name="Convert_162922" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="369" name="self.layers.3.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="370" name="self.layers.3.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="14337136" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="371" name="self.layers.3.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="372" name="self.layers.3.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="373" name="__module.layers.3.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="374" name="Constant_6289" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="14338160" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="375" name="__module.layers.3.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="352">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="376" name="Constant_6443" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="377" name="__module.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="354,value_states.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="378" name="__module.layers.3.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="379" name="__module.layers.3.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="357">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="380" name="__module.layers.3.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787792" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="381" name="__module.layers.3.self_attn/aten::scaled_dot_product_attention/ConvertLike_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="382" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="359,attn_output.13">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="383" name="__module.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="384" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="360">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="385" name="Constant_6444" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="4787800" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="386" name="__module.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="363">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="387" name="self.layers.3.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="14340208" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="388" name="Convert_178120" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="389" name="self.layers.3.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="14602352" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="390" name="Convert_178123" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="391" name="self.layers.3.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="392" name="self.layers.3.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="14602864" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="393" name="self.layers.3.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="394" name="self.layers.3.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>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.layers.3.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="396" name="Constant_6290" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="14603888" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="397" name="__module.layers.3.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="367,input.65">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="398" name="__module.layers.3/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="369,input.67">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="399" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="400" name="__module.layers.3.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="401" name="Constant_6291" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="14605936" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="402" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="403" name="Constant_6292" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="14607984" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="404" name="__module.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="373,input.69">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="405" name="self.layers.3.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 512" offset="14610032" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="406" name="Convert_66646" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="407" name="self.layers.3.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 1" offset="15658608" size="2048" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="408" name="Convert_66649" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="409" name="self.layers.3.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="410" name="self.layers.3.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 1" offset="15660656" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="411" name="self.layers.3.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="412" name="self.layers.3.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="413" name="__module.layers.3.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="414" name="Constant_6293" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 2048" offset="15664752" size="8192" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="415" name="__module.layers.3.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="376,input.71">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="416" name="__module.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="377,input.73">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="417" name="self.layers.3.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 2048" offset="15672944" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="418" name="Convert_71713" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="419" name="self.layers.3.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="16721520" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="420" name="Convert_71716" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="421" name="self.layers.3.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="422" name="self.layers.3.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="16722032" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="423" name="self.layers.3.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="424" name="self.layers.3.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="425" name="__module.layers.3.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="426" name="Constant_6294" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="16723056" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="427" name="__module.layers.3.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="381,input.77">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="428" name="__module.layers.3/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="383,input.79">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="429" name="__module.layers.4.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="430" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="431" name="Constant_6295" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="16725104" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="432" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="433" name="Constant_6296" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="16727152" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="434" name="__module.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>1500</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="408,hidden_states.25">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="435" name="self.layers.4.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="16729200" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="436" name="Convert_193321" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="437" name="self.layers.4.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="16991344" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="438" name="Convert_193324" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="439" name="self.layers.4.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="440" name="self.layers.4.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="16991856" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="441" name="self.layers.4.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="442" name="self.layers.4.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="443" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="444" name="Constant_6297" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="4256284" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="445" name="Multiply_6178" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="446" name="Constant_6298" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="16992880" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="447" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="418,query_states.17">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="448" name="Constant_6445" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="449" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="420,query_states.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="450" name="__module.layers.4.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="451" name="__module.layers.4.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="421">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="452" name="self.layers.4.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="16994928" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="453" name="Convert_188254" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="454" name="self.layers.4.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="17257072" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="455" name="Convert_188257" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="456" name="self.layers.4.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="457" name="self.layers.4.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="17257584" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="458" name="self.layers.4.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="459" name="self.layers.4.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="460" name="__module.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>1500</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="424">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="461" name="Constant_6446" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="462" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="426,key_states.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="463" name="__module.layers.4.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="464" name="__module.layers.4.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="432">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="465" name="self.layers.4.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="17258608" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="466" name="Convert_183187" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="467" name="self.layers.4.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="17520752" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="468" name="Convert_183190" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="469" name="self.layers.4.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="470" name="self.layers.4.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="17521264" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="471" name="self.layers.4.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="472" name="self.layers.4.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="473" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="474" name="Constant_6299" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="17522288" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="475" name="__module.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>1500</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="429">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="476" name="Constant_6447" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="477" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="431,value_states.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="478" name="__module.layers.4.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="479" name="__module.layers.4.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="434">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="480" name="__module.layers.4.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787792" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="481" name="__module.layers.4.self_attn/aten::scaled_dot_product_attention/ConvertLike_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="482" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="436,attn_output.17">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="483" name="__module.layers.4.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="484" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="437">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="485" name="Constant_6448" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="4787800" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="486" name="__module.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>1500</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="440">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="487" name="self.layers.4.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="17524336" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="488" name="Convert_198388" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="489" name="self.layers.4.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="17786480" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="490" name="Convert_198391" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="491" name="self.layers.4.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="492" name="self.layers.4.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="17786992" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="493" name="self.layers.4.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="494" name="self.layers.4.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="495" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="496" name="Constant_6300" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="17788016" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="497" name="__module.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>1500</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="444,input.83">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="498" name="__module.layers.4/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="446,input.85">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="499" name="__module.layers.4.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="500" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="501" name="Constant_6301" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="17790064" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="502" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="503" name="Constant_6302" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="17792112" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="504" name="__module.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>1500</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="450,input.87">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="505" name="self.layers.4.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 512" offset="17794160" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="506" name="Convert_76780" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="507" name="self.layers.4.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 1" offset="18842736" size="2048" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="508" name="Convert_76783" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="509" name="self.layers.4.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="510" name="self.layers.4.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 1" offset="18844784" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="511" name="self.layers.4.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="512" name="self.layers.4.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="513" name="__module.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>1500</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>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="514" name="Constant_6303" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 2048" offset="18848880" size="8192" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="515" name="__module.layers.4.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="453,input.89">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="516" name="__module.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>1500</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="454,input.91">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="517" name="self.layers.4.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 2048" offset="18857072" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="518" name="Convert_81847" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="519" name="self.layers.4.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="19905648" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="520" name="Convert_81850" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="521" name="self.layers.4.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="522" name="self.layers.4.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="19906160" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="523" name="self.layers.4.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="524" name="self.layers.4.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="525" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="526" name="Constant_6304" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="19907184" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="527" name="__module.layers.4.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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.95">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="528" name="__module.layers.4/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="460,input.97">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="529" name="__module.layers.5.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="530" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="531" name="Constant_6305" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="19909232" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="532" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="533" name="Constant_6306" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="19911280" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="534" name="__module.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>1500</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="485,hidden_states.31">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="535" name="self.layers.5.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="19913328" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="536" name="Convert_213589" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="537" name="self.layers.5.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="20175472" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="538" name="Convert_213592" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="539" name="self.layers.5.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="540" name="self.layers.5.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="20175984" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="541" name="self.layers.5.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="542" name="self.layers.5.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="543" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="544" name="Constant_6307" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1" offset="4256284" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="545" name="Multiply_6182" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="546" name="Constant_6308" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="20177008" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="547" name="__module.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>1500</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="495,query_states.21">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="548" name="Constant_6449" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="549" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="497,query_states">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="550" name="__module.layers.5.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="551" name="__module.layers.5.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="498">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="552" name="self.layers.5.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="20179056" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="553" name="Convert_208522" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="554" name="self.layers.5.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="20441200" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="555" name="Convert_208525" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="556" name="self.layers.5.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="557" name="self.layers.5.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="20441712" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="558" name="self.layers.5.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="559" name="self.layers.5.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="560" name="__module.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>1500</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="501">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="561" name="Constant_6450" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="562" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="503,key_states">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="563" name="__module.layers.5.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="564" name="__module.layers.5.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="509">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="565" name="self.layers.5.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="20442736" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="566" name="Convert_203455" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="567" name="self.layers.5.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="20704880" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="568" name="Convert_203458" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="569" name="self.layers.5.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="570" name="self.layers.5.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="20705392" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="571" name="self.layers.5.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="572" name="self.layers.5.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="573" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="574" name="Constant_6309" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="20706416" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="575" name="__module.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>1500</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="506">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="576" name="Constant_6451" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="4258336" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="577" name="__module.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>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="508,value_states">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="578" name="__module.layers.5.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="579" name="__module.layers.5.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</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="511">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="580" name="__module.layers.5.self_attn/aten::scaled_dot_product_attention/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787792" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="581" name="__module.layers.5.self_attn/aten::scaled_dot_product_attention/ConvertLike_1" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="4787796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="582" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32" />
				<port id="4" precision="FP32" />
			</input>
			<output>
				<port id="5" precision="FP32" names="513,attn_output.21">
					<dim>-1</dim>
					<dim>8</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="583" name="__module.layers.5.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="4258368" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="584" name="__module.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>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="514">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>8</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="585" name="Constant_6452" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="4787800" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="586" name="__module.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>1500</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="517">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="587" name="self.layers.5.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 512" offset="20708464" size="262144" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="588" name="Convert_218656" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="589" name="self.layers.5.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="20970608" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="590" name="Convert_218659" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="591" name="self.layers.5.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="592" name="self.layers.5.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="20971120" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="593" name="self.layers.5.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="594" name="self.layers.5.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="595" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="596" name="Constant_6310" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="20972144" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="597" name="__module.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>1500</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="521,input.101">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="598" name="__module.layers.5/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="523,input.103">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="599" name="__module.layers.5.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="600" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="601" name="Constant_6311" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="20974192" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="602" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="603" name="Constant_6312" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="20976240" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="604" name="__module.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>1500</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="527,input.105">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="605" name="self.layers.5.fc1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 512" offset="20978288" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="606" name="Convert_86914" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="607" name="self.layers.5.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="2048, 1" offset="22026864" size="2048" />
			<output>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="608" name="Convert_86917" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="609" name="self.layers.5.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="610" name="self.layers.5.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="2048, 1" offset="22028912" size="4096" />
			<output>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="611" name="self.layers.5.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>2048</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="612" name="self.layers.5.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>2048</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="613" name="__module.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>1500</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>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="614" name="Constant_6313" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 2048" offset="22033008" size="8192" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="615" name="__module.layers.5.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="530,input.107">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="616" name="__module.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>1500</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="531,input.109">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="617" name="self.layers.5.fc2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="512, 2048" offset="22041200" size="1048576" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="618" name="Convert_91981" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="619" name="self.layers.5.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="512, 1" offset="23089776" size="512" />
			<output>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="620" name="Convert_91984" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="621" name="self.layers.5.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="622" name="self.layers.5.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="512, 1" offset="23090288" size="1024" />
			<output>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="623" name="self.layers.5.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>512</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="624" name="self.layers.5.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="625" name="__module.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>1500</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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="626" name="Constant_6314" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="23091312" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="627" name="__module.layers.5.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="535,input.113">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="628" name="__module.layers.5/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="537,input">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="629" name="__module.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="3988504" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="630" name="__module.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="631" name="Constant_6315" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="23093360" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="632" name="__module.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="633" name="Constant_6316" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="23095408" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="634" name="__module.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>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="last_hidden_state">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="635" name="Result_2015" type="Result" version="opset1" output_names="last_hidden_state">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>512</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="9" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
		<edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
		<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
		<edge from-layer="4" from-port="1" to-layer="5" to-port="1" />
		<edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
		<edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
		<edge from-layer="7" from-port="2" to-layer="8" to-port="0" />
		<edge from-layer="8" from-port="1" to-layer="9" to-port="1" />
		<edge from-layer="9" from-port="2" to-layer="11" to-port="0" />
		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
		<edge from-layer="11" from-port="2" to-layer="12" to-port="0" />
		<edge from-layer="12" from-port="1" to-layer="21" to-port="0" />
		<edge from-layer="13" from-port="0" to-layer="14" to-port="0" />
		<edge from-layer="14" from-port="1" to-layer="17" to-port="0" />
		<edge from-layer="15" from-port="0" to-layer="16" to-port="0" />
		<edge from-layer="16" from-port="1" to-layer="17" to-port="1" />
		<edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
		<edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
		<edge from-layer="19" from-port="2" to-layer="20" to-port="0" />
		<edge from-layer="20" from-port="1" to-layer="21" to-port="1" />
		<edge from-layer="21" from-port="2" to-layer="23" to-port="0" />
		<edge from-layer="22" from-port="0" to-layer="23" to-port="1" />
		<edge from-layer="23" from-port="2" to-layer="24" to-port="0" />
		<edge from-layer="24" from-port="1" to-layer="26" to-port="0" />
		<edge from-layer="25" from-port="0" to-layer="26" to-port="1" />
		<edge from-layer="26" from-port="2" to-layer="28" to-port="0" />
		<edge from-layer="27" from-port="0" to-layer="28" to-port="1" />
		<edge from-layer="28" from-port="2" to-layer="98" to-port="0" />
		<edge from-layer="28" from-port="2" to-layer="30" to-port="0" />
		<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
		<edge from-layer="30" from-port="2" to-layer="32" to-port="0" />
		<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
		<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
		<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
		<edge from-layer="34" from-port="2" to-layer="73" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="60" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="43" to-port="0" />
		<edge from-layer="35" from-port="0" to-layer="36" to-port="0" />
		<edge from-layer="36" from-port="1" to-layer="39" to-port="0" />
		<edge from-layer="37" from-port="0" to-layer="38" to-port="0" />
		<edge from-layer="38" from-port="1" to-layer="39" to-port="1" />
		<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
		<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
		<edge from-layer="41" from-port="2" to-layer="42" to-port="0" />
		<edge from-layer="42" from-port="1" to-layer="43" to-port="1" />
		<edge from-layer="43" from-port="2" to-layer="45" to-port="0" />
		<edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
		<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
		<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
		<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
		<edge from-layer="49" from-port="2" to-layer="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="82" to-port="0" />
		<edge from-layer="52" from-port="0" to-layer="53" to-port="0" />
		<edge from-layer="53" from-port="1" to-layer="56" to-port="0" />
		<edge from-layer="54" from-port="0" to-layer="55" to-port="0" />
		<edge from-layer="55" from-port="1" to-layer="56" to-port="1" />
		<edge from-layer="56" from-port="2" to-layer="58" to-port="0" />
		<edge from-layer="57" from-port="0" to-layer="58" to-port="1" />
		<edge from-layer="58" from-port="2" 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="82" to-port="1" />
		<edge from-layer="65" from-port="0" to-layer="66" to-port="0" />
		<edge from-layer="66" from-port="1" to-layer="69" to-port="0" />
		<edge from-layer="67" from-port="0" to-layer="68" to-port="0" />
		<edge from-layer="68" from-port="1" to-layer="69" to-port="1" />
		<edge from-layer="69" from-port="2" to-layer="71" to-port="0" />
		<edge from-layer="70" from-port="0" to-layer="71" to-port="1" />
		<edge from-layer="71" from-port="2" to-layer="72" to-port="0" />
		<edge from-layer="72" from-port="1" to-layer="73" to-port="1" />
		<edge from-layer="73" from-port="2" to-layer="75" to-port="0" />
		<edge from-layer="74" from-port="0" to-layer="75" to-port="1" />
		<edge from-layer="75" from-port="2" to-layer="77" to-port="0" />
		<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
		<edge from-layer="77" from-port="2" to-layer="79" to-port="0" />
		<edge from-layer="78" from-port="0" to-layer="79" to-port="1" />
		<edge from-layer="79" from-port="2" to-layer="82" to-port="2" />
		<edge from-layer="80" from-port="0" to-layer="82" to-port="3" />
		<edge from-layer="81" from-port="0" to-layer="82" to-port="4" />
		<edge from-layer="82" from-port="5" to-layer="84" to-port="0" />
		<edge from-layer="83" from-port="0" to-layer="84" to-port="1" />
		<edge from-layer="84" from-port="2" to-layer="86" to-port="0" />
		<edge from-layer="85" from-port="0" to-layer="86" to-port="1" />
		<edge from-layer="86" from-port="2" to-layer="95" to-port="0" />
		<edge from-layer="87" from-port="0" to-layer="88" to-port="0" />
		<edge from-layer="88" from-port="1" to-layer="91" to-port="0" />
		<edge from-layer="89" from-port="0" to-layer="90" to-port="0" />
		<edge from-layer="90" from-port="1" to-layer="91" to-port="1" />
		<edge from-layer="91" from-port="2" to-layer="93" to-port="0" />
		<edge from-layer="92" from-port="0" to-layer="93" to-port="1" />
		<edge from-layer="93" from-port="2" to-layer="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="98" to-port="1" />
		<edge from-layer="98" from-port="2" to-layer="128" to-port="0" />
		<edge from-layer="98" from-port="2" to-layer="100" to-port="0" />
		<edge from-layer="99" from-port="0" to-layer="100" to-port="1" />
		<edge from-layer="100" from-port="2" to-layer="102" to-port="0" />
		<edge from-layer="101" from-port="0" to-layer="102" to-port="1" />
		<edge from-layer="102" from-port="2" to-layer="104" to-port="0" />
		<edge from-layer="103" from-port="0" to-layer="104" to-port="1" />
		<edge from-layer="104" from-port="2" to-layer="113" to-port="0" />
		<edge from-layer="105" from-port="0" to-layer="106" to-port="0" />
		<edge from-layer="106" from-port="1" to-layer="109" to-port="0" />
		<edge from-layer="107" from-port="0" to-layer="108" to-port="0" />
		<edge from-layer="108" from-port="1" to-layer="109" to-port="1" />
		<edge from-layer="109" from-port="2" to-layer="111" to-port="0" />
		<edge from-layer="110" from-port="0" to-layer="111" to-port="1" />
		<edge from-layer="111" from-port="2" to-layer="112" to-port="0" />
		<edge from-layer="112" from-port="1" to-layer="113" to-port="1" />
		<edge from-layer="113" from-port="2" to-layer="115" to-port="0" />
		<edge from-layer="114" from-port="0" to-layer="115" to-port="1" />
		<edge from-layer="115" from-port="2" to-layer="116" to-port="0" />
		<edge from-layer="116" from-port="1" to-layer="125" to-port="0" />
		<edge from-layer="117" from-port="0" to-layer="118" to-port="0" />
		<edge from-layer="118" from-port="1" to-layer="121" to-port="0" />
		<edge from-layer="119" from-port="0" to-layer="120" to-port="0" />
		<edge from-layer="120" from-port="1" to-layer="121" to-port="1" />
		<edge from-layer="121" from-port="2" to-layer="123" to-port="0" />
		<edge from-layer="122" from-port="0" to-layer="123" to-port="1" />
		<edge from-layer="123" from-port="2" to-layer="124" to-port="0" />
		<edge from-layer="124" from-port="1" to-layer="125" to-port="1" />
		<edge from-layer="125" from-port="2" to-layer="127" to-port="0" />
		<edge from-layer="126" from-port="0" to-layer="127" to-port="1" />
		<edge from-layer="127" from-port="2" to-layer="128" to-port="1" />
		<edge from-layer="128" from-port="2" to-layer="130" to-port="0" />
		<edge from-layer="128" from-port="2" to-layer="198" to-port="0" />
		<edge from-layer="129" from-port="0" to-layer="130" to-port="1" />
		<edge from-layer="130" from-port="2" to-layer="132" to-port="0" />
		<edge from-layer="131" from-port="0" to-layer="132" to-port="1" />
		<edge from-layer="132" from-port="2" to-layer="134" 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="173" to-port="0" />
		<edge from-layer="134" from-port="2" to-layer="160" to-port="0" />
		<edge from-layer="134" from-port="2" to-layer="143" to-port="0" />
		<edge from-layer="135" from-port="0" to-layer="136" to-port="0" />
		<edge from-layer="136" from-port="1" to-layer="139" to-port="0" />
		<edge from-layer="137" from-port="0" to-layer="138" to-port="0" />
		<edge from-layer="138" from-port="1" to-layer="139" to-port="1" />
		<edge from-layer="139" from-port="2" to-layer="141" to-port="0" />
		<edge from-layer="140" from-port="0" to-layer="141" to-port="1" />
		<edge from-layer="141" from-port="2" to-layer="142" to-port="0" />
		<edge from-layer="142" from-port="1" to-layer="143" to-port="1" />
		<edge from-layer="143" from-port="2" to-layer="145" to-port="0" />
		<edge from-layer="144" from-port="0" to-layer="145" to-port="1" />
		<edge from-layer="145" from-port="2" to-layer="147" to-port="0" />
		<edge from-layer="146" from-port="0" to-layer="147" to-port="1" />
		<edge from-layer="147" from-port="2" to-layer="149" to-port="0" />
		<edge from-layer="148" from-port="0" to-layer="149" to-port="1" />
		<edge from-layer="149" from-port="2" to-layer="151" to-port="0" />
		<edge from-layer="150" from-port="0" to-layer="151" to-port="1" />
		<edge from-layer="151" from-port="2" to-layer="182" to-port="0" />
		<edge from-layer="152" from-port="0" to-layer="153" to-port="0" />
		<edge from-layer="153" from-port="1" to-layer="156" to-port="0" />
		<edge from-layer="154" from-port="0" to-layer="155" to-port="0" />
		<edge from-layer="155" from-port="1" to-layer="156" to-port="1" />
		<edge from-layer="156" from-port="2" to-layer="158" to-port="0" />
		<edge from-layer="157" from-port="0" to-layer="158" to-port="1" />
		<edge from-layer="158" from-port="2" to-layer="159" to-port="0" />
		<edge from-layer="159" from-port="1" to-layer="160" to-port="1" />
		<edge from-layer="160" from-port="2" to-layer="162" to-port="0" />
		<edge from-layer="161" from-port="0" to-layer="162" to-port="1" />
		<edge from-layer="162" from-port="2" to-layer="164" to-port="0" />
		<edge from-layer="163" from-port="0" to-layer="164" to-port="1" />
		<edge from-layer="164" from-port="2" to-layer="182" to-port="1" />
		<edge from-layer="165" from-port="0" to-layer="166" to-port="0" />
		<edge from-layer="166" from-port="1" to-layer="169" to-port="0" />
		<edge from-layer="167" from-port="0" to-layer="168" to-port="0" />
		<edge from-layer="168" from-port="1" to-layer="169" to-port="1" />
		<edge from-layer="169" from-port="2" to-layer="171" to-port="0" />
		<edge from-layer="170" from-port="0" to-layer="171" to-port="1" />
		<edge from-layer="171" from-port="2" to-layer="172" to-port="0" />
		<edge from-layer="172" from-port="1" to-layer="173" to-port="1" />
		<edge from-layer="173" from-port="2" to-layer="175" to-port="0" />
		<edge from-layer="174" from-port="0" to-layer="175" to-port="1" />
		<edge from-layer="175" from-port="2" to-layer="177" to-port="0" />
		<edge from-layer="176" from-port="0" to-layer="177" to-port="1" />
		<edge from-layer="177" from-port="2" to-layer="179" to-port="0" />
		<edge from-layer="178" from-port="0" to-layer="179" to-port="1" />
		<edge from-layer="179" from-port="2" to-layer="182" to-port="2" />
		<edge from-layer="180" from-port="0" to-layer="182" to-port="3" />
		<edge from-layer="181" from-port="0" to-layer="182" to-port="4" />
		<edge from-layer="182" from-port="5" to-layer="184" to-port="0" />
		<edge from-layer="183" from-port="0" to-layer="184" to-port="1" />
		<edge from-layer="184" from-port="2" to-layer="186" to-port="0" />
		<edge from-layer="185" from-port="0" to-layer="186" to-port="1" />
		<edge from-layer="186" from-port="2" to-layer="195" 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="191" to-port="0" />
		<edge from-layer="189" from-port="0" to-layer="190" to-port="0" />
		<edge from-layer="190" from-port="1" to-layer="191" to-port="1" />
		<edge from-layer="191" from-port="2" to-layer="193" to-port="0" />
		<edge from-layer="192" from-port="0" to-layer="193" to-port="1" />
		<edge from-layer="193" from-port="2" to-layer="194" to-port="0" />
		<edge from-layer="194" from-port="1" to-layer="195" to-port="1" />
		<edge from-layer="195" from-port="2" to-layer="197" to-port="0" />
		<edge from-layer="196" from-port="0" to-layer="197" to-port="1" />
		<edge from-layer="197" from-port="2" to-layer="198" to-port="1" />
		<edge from-layer="198" from-port="2" to-layer="200" to-port="0" />
		<edge from-layer="198" from-port="2" to-layer="228" 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="202" to-port="0" />
		<edge from-layer="201" from-port="0" to-layer="202" to-port="1" />
		<edge from-layer="202" from-port="2" to-layer="204" to-port="0" />
		<edge from-layer="203" from-port="0" to-layer="204" to-port="1" />
		<edge from-layer="204" from-port="2" to-layer="213" to-port="0" />
		<edge from-layer="205" from-port="0" to-layer="206" to-port="0" />
		<edge from-layer="206" from-port="1" to-layer="209" to-port="0" />
		<edge from-layer="207" from-port="0" to-layer="208" to-port="0" />
		<edge from-layer="208" from-port="1" to-layer="209" to-port="1" />
		<edge from-layer="209" from-port="2" to-layer="211" to-port="0" />
		<edge from-layer="210" from-port="0" to-layer="211" to-port="1" />
		<edge from-layer="211" from-port="2" to-layer="212" to-port="0" />
		<edge from-layer="212" from-port="1" to-layer="213" to-port="1" />
		<edge from-layer="213" from-port="2" to-layer="215" to-port="0" />
		<edge from-layer="214" from-port="0" to-layer="215" to-port="1" />
		<edge from-layer="215" from-port="2" to-layer="216" to-port="0" />
		<edge from-layer="216" from-port="1" to-layer="225" to-port="0" />
		<edge from-layer="217" from-port="0" to-layer="218" to-port="0" />
		<edge from-layer="218" from-port="1" to-layer="221" to-port="0" />
		<edge from-layer="219" from-port="0" to-layer="220" to-port="0" />
		<edge from-layer="220" from-port="1" to-layer="221" to-port="1" />
		<edge from-layer="221" from-port="2" to-layer="223" to-port="0" />
		<edge from-layer="222" from-port="0" to-layer="223" to-port="1" />
		<edge from-layer="223" from-port="2" to-layer="224" to-port="0" />
		<edge from-layer="224" from-port="1" to-layer="225" to-port="1" />
		<edge from-layer="225" from-port="2" to-layer="227" to-port="0" />
		<edge from-layer="226" from-port="0" to-layer="227" to-port="1" />
		<edge from-layer="227" from-port="2" to-layer="228" to-port="1" />
		<edge from-layer="228" from-port="2" to-layer="230" to-port="0" />
		<edge from-layer="228" from-port="2" to-layer="298" to-port="0" />
		<edge from-layer="229" from-port="0" to-layer="230" to-port="1" />
		<edge from-layer="230" from-port="2" to-layer="232" to-port="0" />
		<edge from-layer="231" from-port="0" to-layer="232" to-port="1" />
		<edge from-layer="232" from-port="2" to-layer="234" to-port="0" />
		<edge from-layer="233" from-port="0" to-layer="234" to-port="1" />
		<edge from-layer="234" from-port="2" to-layer="243" to-port="0" />
		<edge from-layer="234" from-port="2" to-layer="273" to-port="0" />
		<edge from-layer="234" from-port="2" to-layer="260" to-port="0" />
		<edge from-layer="235" from-port="0" to-layer="236" to-port="0" />
		<edge from-layer="236" from-port="1" to-layer="239" to-port="0" />
		<edge from-layer="237" from-port="0" to-layer="238" to-port="0" />
		<edge from-layer="238" from-port="1" to-layer="239" to-port="1" />
		<edge from-layer="239" from-port="2" to-layer="241" to-port="0" />
		<edge from-layer="240" from-port="0" to-layer="241" to-port="1" />
		<edge from-layer="241" from-port="2" to-layer="242" to-port="0" />
		<edge from-layer="242" from-port="1" to-layer="243" to-port="1" />
		<edge from-layer="243" from-port="2" to-layer="245" to-port="0" />
		<edge from-layer="244" from-port="0" to-layer="245" to-port="1" />
		<edge from-layer="245" from-port="2" to-layer="247" to-port="0" />
		<edge from-layer="246" from-port="0" to-layer="247" to-port="1" />
		<edge from-layer="247" from-port="2" to-layer="249" to-port="0" />
		<edge from-layer="248" from-port="0" to-layer="249" to-port="1" />
		<edge from-layer="249" from-port="2" to-layer="251" to-port="0" />
		<edge from-layer="250" from-port="0" to-layer="251" to-port="1" />
		<edge from-layer="251" from-port="2" to-layer="282" to-port="0" />
		<edge from-layer="252" from-port="0" to-layer="253" to-port="0" />
		<edge from-layer="253" from-port="1" to-layer="256" to-port="0" />
		<edge from-layer="254" from-port="0" to-layer="255" to-port="0" />
		<edge from-layer="255" from-port="1" to-layer="256" to-port="1" />
		<edge from-layer="256" from-port="2" to-layer="258" to-port="0" />
		<edge from-layer="257" from-port="0" to-layer="258" to-port="1" />
		<edge from-layer="258" from-port="2" to-layer="259" to-port="0" />
		<edge from-layer="259" from-port="1" to-layer="260" to-port="1" />
		<edge from-layer="260" from-port="2" to-layer="262" to-port="0" />
		<edge from-layer="261" from-port="0" to-layer="262" to-port="1" />
		<edge from-layer="262" from-port="2" to-layer="264" to-port="0" />
		<edge from-layer="263" from-port="0" to-layer="264" to-port="1" />
		<edge from-layer="264" from-port="2" to-layer="282" to-port="1" />
		<edge from-layer="265" from-port="0" to-layer="266" to-port="0" />
		<edge from-layer="266" from-port="1" 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="271" to-port="0" />
		<edge from-layer="270" from-port="0" to-layer="271" to-port="1" />
		<edge from-layer="271" from-port="2" to-layer="272" to-port="0" />
		<edge from-layer="272" from-port="1" to-layer="273" to-port="1" />
		<edge from-layer="273" from-port="2" to-layer="275" to-port="0" />
		<edge from-layer="274" from-port="0" to-layer="275" to-port="1" />
		<edge from-layer="275" from-port="2" to-layer="277" to-port="0" />
		<edge from-layer="276" from-port="0" to-layer="277" to-port="1" />
		<edge from-layer="277" from-port="2" to-layer="279" to-port="0" />
		<edge from-layer="278" from-port="0" to-layer="279" to-port="1" />
		<edge from-layer="279" from-port="2" to-layer="282" to-port="2" />
		<edge from-layer="280" from-port="0" to-layer="282" to-port="3" />
		<edge from-layer="281" from-port="0" to-layer="282" to-port="4" />
		<edge from-layer="282" from-port="5" to-layer="284" to-port="0" />
		<edge from-layer="283" from-port="0" to-layer="284" to-port="1" />
		<edge from-layer="284" from-port="2" to-layer="286" to-port="0" />
		<edge from-layer="285" from-port="0" to-layer="286" to-port="1" />
		<edge from-layer="286" from-port="2" to-layer="295" to-port="0" />
		<edge from-layer="287" from-port="0" to-layer="288" to-port="0" />
		<edge from-layer="288" from-port="1" to-layer="291" to-port="0" />
		<edge from-layer="289" from-port="0" to-layer="290" to-port="0" />
		<edge from-layer="290" from-port="1" to-layer="291" to-port="1" />
		<edge from-layer="291" from-port="2" to-layer="293" to-port="0" />
		<edge from-layer="292" from-port="0" to-layer="293" to-port="1" />
		<edge from-layer="293" from-port="2" to-layer="294" to-port="0" />
		<edge from-layer="294" from-port="1" to-layer="295" to-port="1" />
		<edge from-layer="295" from-port="2" to-layer="297" to-port="0" />
		<edge from-layer="296" from-port="0" to-layer="297" to-port="1" />
		<edge from-layer="297" from-port="2" to-layer="298" to-port="1" />
		<edge from-layer="298" from-port="2" to-layer="300" to-port="0" />
		<edge from-layer="298" from-port="2" to-layer="328" to-port="0" />
		<edge from-layer="299" from-port="0" to-layer="300" to-port="1" />
		<edge from-layer="300" from-port="2" to-layer="302" to-port="0" />
		<edge from-layer="301" from-port="0" to-layer="302" to-port="1" />
		<edge from-layer="302" from-port="2" to-layer="304" to-port="0" />
		<edge from-layer="303" from-port="0" to-layer="304" to-port="1" />
		<edge from-layer="304" from-port="2" to-layer="313" to-port="0" />
		<edge from-layer="305" from-port="0" to-layer="306" to-port="0" />
		<edge from-layer="306" from-port="1" to-layer="309" to-port="0" />
		<edge from-layer="307" from-port="0" to-layer="308" to-port="0" />
		<edge from-layer="308" from-port="1" to-layer="309" to-port="1" />
		<edge from-layer="309" from-port="2" to-layer="311" to-port="0" />
		<edge from-layer="310" from-port="0" to-layer="311" to-port="1" />
		<edge from-layer="311" from-port="2" to-layer="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="315" to-port="0" />
		<edge from-layer="314" from-port="0" to-layer="315" to-port="1" />
		<edge from-layer="315" from-port="2" to-layer="316" to-port="0" />
		<edge from-layer="316" from-port="1" to-layer="325" 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="321" to-port="0" />
		<edge from-layer="319" from-port="0" to-layer="320" to-port="0" />
		<edge from-layer="320" from-port="1" to-layer="321" to-port="1" />
		<edge from-layer="321" from-port="2" to-layer="323" to-port="0" />
		<edge from-layer="322" from-port="0" to-layer="323" to-port="1" />
		<edge from-layer="323" from-port="2" to-layer="324" to-port="0" />
		<edge from-layer="324" from-port="1" to-layer="325" to-port="1" />
		<edge from-layer="325" from-port="2" to-layer="327" to-port="0" />
		<edge from-layer="326" from-port="0" to-layer="327" to-port="1" />
		<edge from-layer="327" from-port="2" to-layer="328" to-port="1" />
		<edge from-layer="328" from-port="2" to-layer="330" to-port="0" />
		<edge from-layer="328" from-port="2" to-layer="398" to-port="0" />
		<edge from-layer="329" from-port="0" to-layer="330" to-port="1" />
		<edge from-layer="330" from-port="2" to-layer="332" to-port="0" />
		<edge from-layer="331" from-port="0" to-layer="332" to-port="1" />
		<edge from-layer="332" from-port="2" to-layer="334" to-port="0" />
		<edge from-layer="333" from-port="0" to-layer="334" to-port="1" />
		<edge from-layer="334" from-port="2" to-layer="360" to-port="0" />
		<edge from-layer="334" from-port="2" to-layer="373" to-port="0" />
		<edge from-layer="334" from-port="2" to-layer="343" to-port="0" />
		<edge from-layer="335" from-port="0" to-layer="336" to-port="0" />
		<edge from-layer="336" from-port="1" to-layer="339" to-port="0" />
		<edge from-layer="337" from-port="0" to-layer="338" to-port="0" />
		<edge from-layer="338" from-port="1" to-layer="339" to-port="1" />
		<edge from-layer="339" from-port="2" to-layer="341" to-port="0" />
		<edge from-layer="340" from-port="0" to-layer="341" to-port="1" />
		<edge from-layer="341" from-port="2" to-layer="342" to-port="0" />
		<edge from-layer="342" from-port="1" to-layer="343" to-port="1" />
		<edge from-layer="343" from-port="2" to-layer="345" to-port="0" />
		<edge from-layer="344" from-port="0" to-layer="345" to-port="1" />
		<edge from-layer="345" from-port="2" to-layer="347" to-port="0" />
		<edge from-layer="346" from-port="0" to-layer="347" to-port="1" />
		<edge from-layer="347" from-port="2" to-layer="349" to-port="0" />
		<edge from-layer="348" from-port="0" to-layer="349" to-port="1" />
		<edge from-layer="349" from-port="2" to-layer="351" to-port="0" />
		<edge from-layer="350" from-port="0" to-layer="351" to-port="1" />
		<edge from-layer="351" from-port="2" to-layer="382" to-port="0" />
		<edge from-layer="352" from-port="0" to-layer="353" to-port="0" />
		<edge from-layer="353" from-port="1" to-layer="356" to-port="0" />
		<edge from-layer="354" from-port="0" to-layer="355" to-port="0" />
		<edge from-layer="355" from-port="1" to-layer="356" to-port="1" />
		<edge from-layer="356" from-port="2" to-layer="358" to-port="0" />
		<edge from-layer="357" from-port="0" to-layer="358" to-port="1" />
		<edge from-layer="358" from-port="2" to-layer="359" to-port="0" />
		<edge from-layer="359" from-port="1" to-layer="360" to-port="1" />
		<edge from-layer="360" from-port="2" to-layer="362" to-port="0" />
		<edge from-layer="361" from-port="0" to-layer="362" to-port="1" />
		<edge from-layer="362" from-port="2" to-layer="364" to-port="0" />
		<edge from-layer="363" from-port="0" to-layer="364" to-port="1" />
		<edge from-layer="364" from-port="2" to-layer="382" to-port="1" />
		<edge from-layer="365" from-port="0" to-layer="366" to-port="0" />
		<edge from-layer="366" from-port="1" to-layer="369" to-port="0" />
		<edge from-layer="367" from-port="0" to-layer="368" to-port="0" />
		<edge from-layer="368" from-port="1" to-layer="369" to-port="1" />
		<edge from-layer="369" from-port="2" to-layer="371" to-port="0" />
		<edge from-layer="370" from-port="0" to-layer="371" to-port="1" />
		<edge from-layer="371" from-port="2" to-layer="372" to-port="0" />
		<edge from-layer="372" from-port="1" to-layer="373" to-port="1" />
		<edge from-layer="373" from-port="2" to-layer="375" to-port="0" />
		<edge from-layer="374" from-port="0" to-layer="375" to-port="1" />
		<edge from-layer="375" from-port="2" to-layer="377" to-port="0" />
		<edge from-layer="376" from-port="0" to-layer="377" to-port="1" />
		<edge from-layer="377" from-port="2" to-layer="379" to-port="0" />
		<edge from-layer="378" from-port="0" to-layer="379" to-port="1" />
		<edge from-layer="379" from-port="2" to-layer="382" to-port="2" />
		<edge from-layer="380" from-port="0" to-layer="382" to-port="3" />
		<edge from-layer="381" from-port="0" to-layer="382" to-port="4" />
		<edge from-layer="382" from-port="5" 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="395" to-port="0" />
		<edge from-layer="387" from-port="0" to-layer="388" to-port="0" />
		<edge from-layer="388" from-port="1" to-layer="391" to-port="0" />
		<edge from-layer="389" from-port="0" to-layer="390" to-port="0" />
		<edge from-layer="390" from-port="1" to-layer="391" to-port="1" />
		<edge from-layer="391" from-port="2" to-layer="393" to-port="0" />
		<edge from-layer="392" from-port="0" to-layer="393" to-port="1" />
		<edge from-layer="393" from-port="2" 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="397" to-port="0" />
		<edge from-layer="396" from-port="0" to-layer="397" to-port="1" />
		<edge from-layer="397" from-port="2" to-layer="398" to-port="1" />
		<edge from-layer="398" from-port="2" to-layer="400" to-port="0" />
		<edge from-layer="398" from-port="2" to-layer="428" to-port="0" />
		<edge from-layer="399" from-port="0" to-layer="400" to-port="1" />
		<edge from-layer="400" from-port="2" to-layer="402" to-port="0" />
		<edge from-layer="401" from-port="0" to-layer="402" to-port="1" />
		<edge from-layer="402" from-port="2" to-layer="404" to-port="0" />
		<edge from-layer="403" from-port="0" to-layer="404" to-port="1" />
		<edge from-layer="404" from-port="2" to-layer="413" 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="409" to-port="0" />
		<edge from-layer="407" from-port="0" to-layer="408" to-port="0" />
		<edge from-layer="408" from-port="1" to-layer="409" to-port="1" />
		<edge from-layer="409" from-port="2" to-layer="411" to-port="0" />
		<edge from-layer="410" from-port="0" to-layer="411" to-port="1" />
		<edge from-layer="411" from-port="2" to-layer="412" to-port="0" />
		<edge from-layer="412" from-port="1" to-layer="413" to-port="1" />
		<edge from-layer="413" from-port="2" to-layer="415" to-port="0" />
		<edge from-layer="414" from-port="0" to-layer="415" to-port="1" />
		<edge from-layer="415" from-port="2" to-layer="416" to-port="0" />
		<edge from-layer="416" from-port="1" to-layer="425" to-port="0" />
		<edge from-layer="417" from-port="0" to-layer="418" to-port="0" />
		<edge from-layer="418" from-port="1" to-layer="421" to-port="0" />
		<edge from-layer="419" from-port="0" to-layer="420" to-port="0" />
		<edge from-layer="420" from-port="1" to-layer="421" to-port="1" />
		<edge from-layer="421" from-port="2" to-layer="423" to-port="0" />
		<edge from-layer="422" from-port="0" to-layer="423" to-port="1" />
		<edge from-layer="423" from-port="2" to-layer="424" to-port="0" />
		<edge from-layer="424" from-port="1" to-layer="425" to-port="1" />
		<edge from-layer="425" from-port="2" to-layer="427" to-port="0" />
		<edge from-layer="426" from-port="0" to-layer="427" to-port="1" />
		<edge from-layer="427" from-port="2" to-layer="428" to-port="1" />
		<edge from-layer="428" from-port="2" to-layer="430" to-port="0" />
		<edge from-layer="428" from-port="2" to-layer="498" to-port="0" />
		<edge from-layer="429" from-port="0" to-layer="430" to-port="1" />
		<edge from-layer="430" from-port="2" to-layer="432" to-port="0" />
		<edge from-layer="431" from-port="0" to-layer="432" to-port="1" />
		<edge from-layer="432" from-port="2" to-layer="434" to-port="0" />
		<edge from-layer="433" from-port="0" to-layer="434" to-port="1" />
		<edge from-layer="434" from-port="2" to-layer="460" to-port="0" />
		<edge from-layer="434" from-port="2" to-layer="473" to-port="0" />
		<edge from-layer="434" from-port="2" to-layer="443" to-port="0" />
		<edge from-layer="435" from-port="0" to-layer="436" to-port="0" />
		<edge from-layer="436" from-port="1" to-layer="439" to-port="0" />
		<edge from-layer="437" from-port="0" to-layer="438" to-port="0" />
		<edge from-layer="438" from-port="1" to-layer="439" to-port="1" />
		<edge from-layer="439" from-port="2" to-layer="441" to-port="0" />
		<edge from-layer="440" from-port="0" to-layer="441" to-port="1" />
		<edge from-layer="441" from-port="2" to-layer="442" to-port="0" />
		<edge from-layer="442" from-port="1" to-layer="443" to-port="1" />
		<edge from-layer="443" from-port="2" to-layer="445" to-port="0" />
		<edge from-layer="444" from-port="0" to-layer="445" to-port="1" />
		<edge from-layer="445" from-port="2" to-layer="447" to-port="0" />
		<edge from-layer="446" from-port="0" to-layer="447" to-port="1" />
		<edge from-layer="447" from-port="2" to-layer="449" to-port="0" />
		<edge from-layer="448" from-port="0" to-layer="449" to-port="1" />
		<edge from-layer="449" from-port="2" to-layer="451" to-port="0" />
		<edge from-layer="450" from-port="0" to-layer="451" to-port="1" />
		<edge from-layer="451" from-port="2" to-layer="482" to-port="0" />
		<edge from-layer="452" from-port="0" to-layer="453" to-port="0" />
		<edge from-layer="453" from-port="1" to-layer="456" to-port="0" />
		<edge from-layer="454" from-port="0" to-layer="455" to-port="0" />
		<edge from-layer="455" from-port="1" to-layer="456" to-port="1" />
		<edge from-layer="456" from-port="2" to-layer="458" to-port="0" />
		<edge from-layer="457" from-port="0" to-layer="458" to-port="1" />
		<edge from-layer="458" from-port="2" to-layer="459" to-port="0" />
		<edge from-layer="459" from-port="1" to-layer="460" to-port="1" />
		<edge from-layer="460" from-port="2" to-layer="462" to-port="0" />
		<edge from-layer="461" from-port="0" to-layer="462" to-port="1" />
		<edge from-layer="462" from-port="2" to-layer="464" to-port="0" />
		<edge from-layer="463" from-port="0" to-layer="464" to-port="1" />
		<edge from-layer="464" from-port="2" to-layer="482" to-port="1" />
		<edge from-layer="465" from-port="0" to-layer="466" to-port="0" />
		<edge from-layer="466" from-port="1" to-layer="469" to-port="0" />
		<edge from-layer="467" from-port="0" to-layer="468" to-port="0" />
		<edge from-layer="468" from-port="1" to-layer="469" to-port="1" />
		<edge from-layer="469" from-port="2" to-layer="471" to-port="0" />
		<edge from-layer="470" from-port="0" to-layer="471" to-port="1" />
		<edge from-layer="471" from-port="2" to-layer="472" to-port="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="479" to-port="0" />
		<edge from-layer="478" from-port="0" to-layer="479" to-port="1" />
		<edge from-layer="479" from-port="2" to-layer="482" to-port="2" />
		<edge from-layer="480" from-port="0" to-layer="482" to-port="3" />
		<edge from-layer="481" from-port="0" to-layer="482" to-port="4" />
		<edge from-layer="482" from-port="5" to-layer="484" to-port="0" />
		<edge from-layer="483" from-port="0" to-layer="484" to-port="1" />
		<edge from-layer="484" from-port="2" to-layer="486" to-port="0" />
		<edge from-layer="485" from-port="0" to-layer="486" to-port="1" />
		<edge from-layer="486" from-port="2" to-layer="495" to-port="0" />
		<edge from-layer="487" from-port="0" to-layer="488" to-port="0" />
		<edge from-layer="488" from-port="1" to-layer="491" to-port="0" />
		<edge from-layer="489" from-port="0" to-layer="490" to-port="0" />
		<edge from-layer="490" from-port="1" to-layer="491" to-port="1" />
		<edge from-layer="491" from-port="2" to-layer="493" to-port="0" />
		<edge from-layer="492" from-port="0" to-layer="493" to-port="1" />
		<edge from-layer="493" from-port="2" to-layer="494" to-port="0" />
		<edge from-layer="494" from-port="1" to-layer="495" to-port="1" />
		<edge from-layer="495" from-port="2" to-layer="497" to-port="0" />
		<edge from-layer="496" from-port="0" to-layer="497" to-port="1" />
		<edge from-layer="497" from-port="2" to-layer="498" to-port="1" />
		<edge from-layer="498" from-port="2" to-layer="500" to-port="0" />
		<edge from-layer="498" from-port="2" to-layer="528" to-port="0" />
		<edge from-layer="499" from-port="0" to-layer="500" to-port="1" />
		<edge from-layer="500" from-port="2" to-layer="502" to-port="0" />
		<edge from-layer="501" from-port="0" to-layer="502" to-port="1" />
		<edge from-layer="502" from-port="2" to-layer="504" to-port="0" />
		<edge from-layer="503" from-port="0" to-layer="504" to-port="1" />
		<edge from-layer="504" from-port="2" to-layer="513" to-port="0" />
		<edge from-layer="505" from-port="0" to-layer="506" to-port="0" />
		<edge from-layer="506" from-port="1" to-layer="509" to-port="0" />
		<edge from-layer="507" from-port="0" to-layer="508" to-port="0" />
		<edge from-layer="508" from-port="1" to-layer="509" to-port="1" />
		<edge from-layer="509" from-port="2" to-layer="511" to-port="0" />
		<edge from-layer="510" from-port="0" to-layer="511" to-port="1" />
		<edge from-layer="511" from-port="2" to-layer="512" to-port="0" />
		<edge from-layer="512" from-port="1" to-layer="513" to-port="1" />
		<edge from-layer="513" from-port="2" to-layer="515" to-port="0" />
		<edge from-layer="514" from-port="0" to-layer="515" to-port="1" />
		<edge from-layer="515" from-port="2" to-layer="516" to-port="0" />
		<edge from-layer="516" from-port="1" to-layer="525" to-port="0" />
		<edge from-layer="517" from-port="0" to-layer="518" to-port="0" />
		<edge from-layer="518" from-port="1" to-layer="521" to-port="0" />
		<edge from-layer="519" from-port="0" to-layer="520" to-port="0" />
		<edge from-layer="520" from-port="1" to-layer="521" to-port="1" />
		<edge from-layer="521" from-port="2" to-layer="523" to-port="0" />
		<edge from-layer="522" from-port="0" to-layer="523" to-port="1" />
		<edge from-layer="523" from-port="2" to-layer="524" to-port="0" />
		<edge from-layer="524" from-port="1" to-layer="525" to-port="1" />
		<edge from-layer="525" from-port="2" to-layer="527" to-port="0" />
		<edge from-layer="526" from-port="0" to-layer="527" to-port="1" />
		<edge from-layer="527" from-port="2" to-layer="528" to-port="1" />
		<edge from-layer="528" from-port="2" to-layer="530" to-port="0" />
		<edge from-layer="528" from-port="2" to-layer="598" 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="532" to-port="0" />
		<edge from-layer="531" from-port="0" to-layer="532" to-port="1" />
		<edge from-layer="532" from-port="2" to-layer="534" to-port="0" />
		<edge from-layer="533" from-port="0" to-layer="534" to-port="1" />
		<edge from-layer="534" from-port="2" to-layer="560" to-port="0" />
		<edge from-layer="534" from-port="2" to-layer="573" to-port="0" />
		<edge from-layer="534" from-port="2" to-layer="543" to-port="0" />
		<edge from-layer="535" from-port="0" to-layer="536" to-port="0" />
		<edge from-layer="536" from-port="1" 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="541" to-port="0" />
		<edge from-layer="540" from-port="0" to-layer="541" to-port="1" />
		<edge from-layer="541" from-port="2" to-layer="542" to-port="0" />
		<edge from-layer="542" from-port="1" to-layer="543" to-port="1" />
		<edge from-layer="543" from-port="2" to-layer="545" to-port="0" />
		<edge from-layer="544" from-port="0" to-layer="545" to-port="1" />
		<edge from-layer="545" from-port="2" to-layer="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="551" to-port="0" />
		<edge from-layer="550" from-port="0" to-layer="551" to-port="1" />
		<edge from-layer="551" from-port="2" to-layer="582" to-port="0" />
		<edge from-layer="552" from-port="0" to-layer="553" to-port="0" />
		<edge from-layer="553" from-port="1" to-layer="556" to-port="0" />
		<edge from-layer="554" from-port="0" to-layer="555" to-port="0" />
		<edge from-layer="555" from-port="1" to-layer="556" to-port="1" />
		<edge from-layer="556" from-port="2" to-layer="558" to-port="0" />
		<edge from-layer="557" from-port="0" to-layer="558" to-port="1" />
		<edge from-layer="558" from-port="2" to-layer="559" to-port="0" />
		<edge from-layer="559" from-port="1" to-layer="560" to-port="1" />
		<edge from-layer="560" from-port="2" to-layer="562" to-port="0" />
		<edge from-layer="561" from-port="0" to-layer="562" to-port="1" />
		<edge from-layer="562" from-port="2" to-layer="564" to-port="0" />
		<edge from-layer="563" from-port="0" to-layer="564" to-port="1" />
		<edge from-layer="564" from-port="2" to-layer="582" to-port="1" />
		<edge from-layer="565" from-port="0" to-layer="566" to-port="0" />
		<edge from-layer="566" from-port="1" to-layer="569" to-port="0" />
		<edge from-layer="567" from-port="0" to-layer="568" to-port="0" />
		<edge from-layer="568" from-port="1" to-layer="569" to-port="1" />
		<edge from-layer="569" from-port="2" to-layer="571" to-port="0" />
		<edge from-layer="570" from-port="0" to-layer="571" to-port="1" />
		<edge from-layer="571" from-port="2" to-layer="572" to-port="0" />
		<edge from-layer="572" from-port="1" to-layer="573" to-port="1" />
		<edge from-layer="573" from-port="2" to-layer="575" to-port="0" />
		<edge from-layer="574" from-port="0" to-layer="575" to-port="1" />
		<edge from-layer="575" from-port="2" to-layer="577" to-port="0" />
		<edge from-layer="576" from-port="0" to-layer="577" to-port="1" />
		<edge from-layer="577" from-port="2" to-layer="579" to-port="0" />
		<edge from-layer="578" from-port="0" to-layer="579" to-port="1" />
		<edge from-layer="579" from-port="2" to-layer="582" to-port="2" />
		<edge from-layer="580" from-port="0" to-layer="582" to-port="3" />
		<edge from-layer="581" from-port="0" to-layer="582" to-port="4" />
		<edge from-layer="582" from-port="5" to-layer="584" to-port="0" />
		<edge from-layer="583" from-port="0" to-layer="584" to-port="1" />
		<edge from-layer="584" from-port="2" to-layer="586" to-port="0" />
		<edge from-layer="585" from-port="0" to-layer="586" to-port="1" />
		<edge from-layer="586" from-port="2" to-layer="595" to-port="0" />
		<edge from-layer="587" from-port="0" to-layer="588" to-port="0" />
		<edge from-layer="588" from-port="1" to-layer="591" to-port="0" />
		<edge from-layer="589" from-port="0" to-layer="590" to-port="0" />
		<edge from-layer="590" from-port="1" to-layer="591" to-port="1" />
		<edge from-layer="591" from-port="2" to-layer="593" to-port="0" />
		<edge from-layer="592" from-port="0" to-layer="593" to-port="1" />
		<edge from-layer="593" from-port="2" to-layer="594" to-port="0" />
		<edge from-layer="594" from-port="1" to-layer="595" to-port="1" />
		<edge from-layer="595" from-port="2" to-layer="597" to-port="0" />
		<edge from-layer="596" from-port="0" to-layer="597" to-port="1" />
		<edge from-layer="597" from-port="2" to-layer="598" to-port="1" />
		<edge from-layer="598" from-port="2" to-layer="628" to-port="0" />
		<edge from-layer="598" from-port="2" to-layer="600" to-port="0" />
		<edge from-layer="599" from-port="0" to-layer="600" to-port="1" />
		<edge from-layer="600" from-port="2" to-layer="602" to-port="0" />
		<edge from-layer="601" from-port="0" 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="613" to-port="0" />
		<edge from-layer="605" from-port="0" to-layer="606" to-port="0" />
		<edge from-layer="606" from-port="1" to-layer="609" 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="609" to-port="1" />
		<edge from-layer="609" from-port="2" to-layer="611" to-port="0" />
		<edge from-layer="610" from-port="0" to-layer="611" to-port="1" />
		<edge from-layer="611" from-port="2" to-layer="612" to-port="0" />
		<edge from-layer="612" from-port="1" to-layer="613" to-port="1" />
		<edge from-layer="613" from-port="2" to-layer="615" to-port="0" />
		<edge from-layer="614" from-port="0" to-layer="615" to-port="1" />
		<edge from-layer="615" from-port="2" to-layer="616" to-port="0" />
		<edge from-layer="616" from-port="1" to-layer="625" 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="621" to-port="0" />
		<edge from-layer="619" from-port="0" to-layer="620" to-port="0" />
		<edge from-layer="620" from-port="1" 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="0" />
		<edge from-layer="624" from-port="1" to-layer="625" to-port="1" />
		<edge from-layer="625" from-port="2" to-layer="627" to-port="0" />
		<edge from-layer="626" from-port="0" to-layer="627" to-port="1" />
		<edge from-layer="627" from-port="2" to-layer="628" to-port="1" />
		<edge from-layer="628" from-port="2" to-layer="630" to-port="0" />
		<edge from-layer="629" from-port="0" to-layer="630" to-port="1" />
		<edge from-layer="630" from-port="2" to-layer="632" to-port="0" />
		<edge from-layer="631" from-port="0" to-layer="632" to-port="1" />
		<edge from-layer="632" from-port="2" to-layer="634" to-port="0" />
		<edge from-layer="633" from-port="0" to-layer="634" to-port="1" />
		<edge from-layer="634" from-port="2" to-layer="635" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2026.0.0-20965-c6d6a13a886-releases/2026/0" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<nncf>
			<friendly_names_were_updated value="True" />
			<version value="3.0.0" />
			<weight_compression>
				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None, 'adaptive_codebook_params': {'value_type': 'f8e4m3', 'across_blocks': False, 'num_elements': 16}}" />
				<all_layers value="False" />
				<awq value="False" />
				<backup_mode value="int8_asym" />
				<compression_format value="dequantize" />
				<gptq value="False" />
				<group_size value="-1" />
				<ignored_scope value="[]" />
				<lora_correction value="False" />
				<mode value="int8_asym" />
				<ratio value="1.0" />
				<scale_estimation value="False" />
				<sensitivity_metric value="weight_quantization_error" />
			</weight_compression>
		</nncf>
		<optimum>
			<nncf_version value="3.0.0" />
			<optimum_intel_version value="1.27.0" />
			<optimum_version value="2.1.0" />
			<pytorch_version value="2.10.0+cpu" />
			<transformers_version value="4.57.6" />
		</optimum>
	</rt_info>
</net>