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="?,80,3000" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="input_features">
					<dim>-1</dim>
					<dim>80</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="self.conv1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 80, 3" offset="0" size="184320" />
			<output>
				<port id="0" precision="FP16" names="self.conv1.weight">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="self.conv1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="__module.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
			<data strides="1" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>80</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="__module.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 384, 1" offset="184320" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="__module.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="__module.conv1/aten::_convolution/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="47">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="17">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="self.conv2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384, 3" offset="185088" size="884736" />
			<output>
				<port id="0" precision="FP16" names="self.conv2.weight">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="self.conv2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="__module.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
			<data strides="2" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="__module.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 384, 1" offset="1069824" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="__module.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="__module.conv2/aten::_convolution/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="59">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="aten::gelu/Gelu_1" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="20,inputs_embeds.1">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="Constant_116" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="1070592" size="24" />
			<output>
				<port id="0" precision="I64" names="24">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="aten::permute/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="25,inputs_embeds">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="Constant_4296_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1500, 384" offset="1070616" size="1152000" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="18" name="Constant_4296" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="27,input.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="20" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="21" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="Constant_4297_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="2222620" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="Constant_4297" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="24" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="Constant_4298_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="2223388" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="26" name="Constant_4298" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="27" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="84,hidden_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="Constant_4241_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="2224156" size="294912" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="29" name="Constant_4241" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="Multiply_4224" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="31" name="Constant_4299_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="2519068" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="Constant_4299" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="__module.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="94,tensor.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="Constant_4375" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="__module.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="96">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="__module.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="__module.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="97">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="self.layers.0.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="2519884" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.0.self_attn.k_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="self.layers.0.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="__module.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="100,tensor.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="Constant_4376" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="__module.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="102">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="__module.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="__module.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="103">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="__module.layers.0.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="113,input.3">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="__module.layers.0.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="114,input.5">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="self.layers.0.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="2814796" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.0.self_attn.v_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="self.layers.0.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="__module.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="Constant_4300_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="3109708" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="Constant_4300" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="__module.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="107,tensor.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="Constant_4377" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="__module.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="109">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="__module.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="__module.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="110">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="__module.layers.0.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="116,attn_output.1">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="__module.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="__module.layers.0.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="117,attn_output.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="60" name="Constant_4378" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3110476" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="__module.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="119">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="self.layers.0.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="3110500" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.0.self_attn.out_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="self.layers.0.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="__module.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="Constant_4301_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="3405412" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Constant_4301" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="__module.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="122,input.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="__module.layers.0/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="124,residual.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="70" name="__module.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="Constant_4302_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="3406180" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="Constant_4302" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="73" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="Constant_4303_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="3406948" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="Constant_4303" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="__module.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="128">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="self.layers.0.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 384" offset="3407716" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.0.fc1.weight">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="self.layers.0.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="Constant_4304_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1536" offset="4587364" size="3072" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="Constant_4304" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="82" name="__module.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="131">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="__module.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="132,input.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="self.layers.0.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 1536" offset="4590436" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.0.fc2.weight">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="self.layers.0.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="__module.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="Constant_4305_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="5770084" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="Constant_4305" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="136,input.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="__module.layers.0/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="138,residual.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="Constant_4306_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="5770852" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="Constant_4306" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="Constant_4307_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="5771620" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="Constant_4307" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="163,hidden_states.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="Constant_4244_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="5772388" size="294912" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="Constant_4244" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="Multiply_4228" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="Constant_4308_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="6067300" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="Constant_4308" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="__module.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="173,tensor.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="Constant_4379" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="__module.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="175">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="__module.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="__module.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="176">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="self.layers.1.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="6068068" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.1.self_attn.k_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="self.layers.1.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="__module.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="179,tensor.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="Constant_4380" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="__module.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="181">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="__module.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="__module.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="182">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="__module.layers.1.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="192,input.13">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="__module.layers.1.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="193,input.15">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="self.layers.1.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="6362980" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.1.self_attn.v_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="self.layers.1.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="__module.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="Constant_4309_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="6657892" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="Constant_4309" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="__module.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="186,tensor.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="124" name="Constant_4381" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="__module.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="188">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="__module.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="__module.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="189">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="__module.layers.1.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="195,attn_output.5">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="__module.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="__module.layers.1.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="196,attn_output.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="Constant_4382" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3110476" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="__module.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="198">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="self.layers.1.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="6658660" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.1.self_attn.out_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="self.layers.1.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="135" name="__module.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="Constant_4310_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="6953572" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="Constant_4310" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="__module.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="201,input.17">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="__module.layers.1/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="203,residual.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="__module.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="Constant_4311_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="6954340" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="Constant_4311" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="Constant_4312_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="6955108" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="Constant_4312" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="__module.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="207">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="self.layers.1.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 384" offset="6955876" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.1.fc1.weight">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="self.layers.1.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="__module.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="Constant_4313_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1536" offset="8135524" size="3072" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="Constant_4313" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="__module.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="210">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="__module.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="211,input.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="self.layers.1.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 1536" offset="8138596" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.1.fc2.weight">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="self.layers.1.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="__module.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="Constant_4314_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="9318244" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="159" name="Constant_4314" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="__module.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="215,input.21">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="__module.layers.1/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="217,residual.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="Constant_4315_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="9319012" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="Constant_4315" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="Constant_4316_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="9319780" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="168" name="Constant_4316" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="242,hidden_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="Constant_4247_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="9320548" size="294912" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="171" name="Constant_4247" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="Multiply_4232" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="Constant_4317_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="9615460" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="Constant_4317" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="__module.layers.2.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="252,tensor.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="Constant_4383" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="177" name="__module.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="254">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="__module.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="__module.layers.2.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="255">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="180" name="self.layers.2.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="9616228" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.2.self_attn.k_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="181" name="self.layers.2.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="__module.layers.2.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="258,tensor.15">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="Constant_4384" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="__module.layers.2.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="260">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="__module.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="__module.layers.2.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="261">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="__module.layers.2.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="271,input.23">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="__module.layers.2.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="272,input.25">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="self.layers.2.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="9911140" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.2.self_attn.v_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="self.layers.2.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="__module.layers.2.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="Constant_4318_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="10206052" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="193" name="Constant_4318" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="__module.layers.2.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="265,tensor.17">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="Constant_4385" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="196" name="__module.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="267">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="198" name="__module.layers.2.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="268">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.layers.2.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="274,attn_output.9">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="__module.layers.2.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="201" name="__module.layers.2.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="275,attn_output.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="Constant_4386" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3110476" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="203" name="__module.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="277">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="self.layers.2.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="10206820" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.2.self_attn.out_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="self.layers.2.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="__module.layers.2.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="Constant_4319_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="10501732" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="Constant_4319" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="__module.layers.2.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="280,input.27">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="__module.layers.2/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="282,residual.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="__module.layers.2.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="Constant_4320_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="10502500" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="214" name="Constant_4320" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="Constant_4321_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="10503268" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="217" name="Constant_4321" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="218" name="__module.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="286">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="219" name="self.layers.2.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 384" offset="10504036" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.2.fc1.weight">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="self.layers.2.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="221" name="__module.layers.2.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="222" name="Constant_4322_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1536" offset="11683684" size="3072" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="Constant_4322" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="__module.layers.2.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="289">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="__module.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="290,input.29">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="self.layers.2.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 1536" offset="11686756" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.2.fc2.weight">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="self.layers.2.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="__module.layers.2.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="Constant_4323_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="12866404" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="230" name="Constant_4323" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="__module.layers.2.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="294,input.31">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="__module.layers.2/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="296,residual.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="233" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="235" name="Constant_4324_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="12867172" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="236" name="Constant_4324" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="Constant_4325_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="12867940" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="239" name="Constant_4325" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="321,hidden_states.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="Constant_4250_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="12868708" size="294912" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="242" name="Constant_4250" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="Multiply_4236" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="244" name="Constant_4326_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="13163620" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="Constant_4326" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="__module.layers.3.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="331,tensor.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="247" name="Constant_4387" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="248" name="__module.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="333">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="249" name="__module.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="250" name="__module.layers.3.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="334">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="self.layers.3.self_attn.k_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="13164388" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.3.self_attn.k_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="252" name="self.layers.3.self_attn.k_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="253" name="__module.layers.3.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="337,tensor.21">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="254" name="Constant_4388" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="__module.layers.3.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="339">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="256" name="__module.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="257" name="__module.layers.3.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="340">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="258" name="__module.layers.3.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="350,input.33">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="259" name="__module.layers.3.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="351,input.35">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="self.layers.3.self_attn.v_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="13459300" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.3.self_attn.v_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="self.layers.3.self_attn.v_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="__module.layers.3.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="Constant_4327_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="13754212" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="Constant_4327" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="__module.layers.3.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="344,tensor">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="Constant_4389" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2519836" size="32" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="__module.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="346">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="__module.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="269" name="__module.layers.3.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="347">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="__module.layers.3.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="353,attn_output.13">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="__module.layers.3.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2519868" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="272" name="__module.layers.3.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="354,attn_output">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="Constant_4390" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3110476" size="24" />
			<rt_info>
				<attribute name="precise" version="0" />
			</rt_info>
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="__module.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="356">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="self.layers.3.self_attn.out_proj.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 384" offset="13754980" size="294912" />
			<output>
				<port id="0" precision="FP16" names="self.layers.3.self_attn.out_proj.weight">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="self.layers.3.self_attn.out_proj.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="__module.layers.3.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="Constant_4328_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="14049892" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="Constant_4328" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="__module.layers.3.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="359,input.37">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="281" name="__module.layers.3/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="361,residual">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="__module.layers.3.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="Constant_4329_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="14050660" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="Constant_4329" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="287" name="Constant_4330_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="14051428" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="Constant_4330" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="289" name="__module.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="365">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="self.layers.3.fc1.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 384" offset="14052196" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.3.fc1.weight">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="self.layers.3.fc1.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="__module.layers.3.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="Constant_4331_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 1536" offset="15231844" size="3072" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="Constant_4331" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="__module.layers.3.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="368">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="__module.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="369,input.39">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="self.layers.3.fc2.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="384, 1536" offset="15234916" size="1179648" />
			<output>
				<port id="0" precision="FP16" names="self.layers.3.fc2.weight">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="self.layers.3.fc2.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="__module.layers.3.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="Constant_4332_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="16414564" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="301" name="Constant_4332" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="__module.layers.3.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="373,input">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="__module.layers.3/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="375">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="__module.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2222616" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="305" name="__module.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="Constant_4333_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="16415332" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="Constant_4333" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="__module.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="Constant_4334_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 1, 384" offset="16416100" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="Constant_4334" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="__module.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="last_hidden_state">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="Result_2149" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="3" 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="3" to-port="1" />
		<edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
		<edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
		<edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
		<edge from-layer="7" from-port="1" to-layer="10" to-port="0" />
		<edge from-layer="8" from-port="0" to-layer="9" to-port="0" />
		<edge from-layer="9" from-port="1" to-layer="10" to-port="1" />
		<edge from-layer="10" from-port="2" to-layer="13" to-port="0" />
		<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
		<edge from-layer="12" from-port="1" to-layer="13" to-port="1" />
		<edge from-layer="13" from-port="2" to-layer="14" to-port="0" />
		<edge from-layer="14" from-port="1" to-layer="16" to-port="0" />
		<edge from-layer="15" from-port="0" to-layer="16" to-port="1" />
		<edge from-layer="16" from-port="2" to-layer="19" to-port="0" />
		<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
		<edge from-layer="18" from-port="1" to-layer="19" to-port="1" />
		<edge from-layer="19" from-port="2" to-layer="21" to-port="0" />
		<edge from-layer="19" from-port="2" to-layer="68" to-port="0" />
		<edge from-layer="20" from-port="0" to-layer="21" to-port="1" />
		<edge from-layer="21" from-port="2" to-layer="24" to-port="0" />
		<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
		<edge from-layer="23" from-port="1" to-layer="24" to-port="1" />
		<edge from-layer="24" from-port="2" to-layer="27" to-port="0" />
		<edge from-layer="25" from-port="0" to-layer="26" to-port="0" />
		<edge from-layer="26" from-port="1" to-layer="27" to-port="1" />
		<edge from-layer="27" from-port="2" to-layer="49" to-port="0" />
		<edge from-layer="27" from-port="2" to-layer="40" to-port="0" />
		<edge from-layer="27" from-port="2" to-layer="30" to-port="0" />
		<edge from-layer="28" from-port="0" to-layer="29" to-port="0" />
		<edge from-layer="29" from-port="1" to-layer="30" to-port="1" />
		<edge from-layer="30" from-port="2" to-layer="33" to-port="0" />
		<edge from-layer="31" from-port="0" to-layer="32" to-port="0" />
		<edge from-layer="32" from-port="1" to-layer="33" to-port="1" />
		<edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
		<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
		<edge from-layer="35" from-port="2" to-layer="37" to-port="0" />
		<edge from-layer="36" from-port="0" to-layer="37" to-port="1" />
		<edge from-layer="37" from-port="2" to-layer="45" to-port="0" />
		<edge from-layer="38" from-port="0" to-layer="39" to-port="0" />
		<edge from-layer="39" from-port="1" to-layer="40" to-port="1" />
		<edge from-layer="40" from-port="2" to-layer="42" to-port="0" />
		<edge from-layer="41" from-port="0" to-layer="42" to-port="1" />
		<edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
		<edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
		<edge from-layer="44" from-port="2" to-layer="45" to-port="1" />
		<edge from-layer="45" from-port="2" to-layer="46" to-port="0" />
		<edge from-layer="46" from-port="1" to-layer="57" to-port="0" />
		<edge from-layer="47" from-port="0" to-layer="48" to-port="0" />
		<edge from-layer="48" from-port="1" to-layer="49" to-port="1" />
		<edge from-layer="49" from-port="2" to-layer="52" to-port="0" />
		<edge from-layer="50" from-port="0" to-layer="51" to-port="0" />
		<edge from-layer="51" from-port="1" to-layer="52" to-port="1" />
		<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
		<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
		<edge from-layer="54" from-port="2" to-layer="56" to-port="0" />
		<edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
		<edge from-layer="56" from-port="2" to-layer="57" to-port="1" />
		<edge from-layer="57" from-port="2" to-layer="59" to-port="0" />
		<edge from-layer="58" from-port="0" to-layer="59" to-port="1" />
		<edge from-layer="59" from-port="2" to-layer="61" to-port="0" />
		<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
		<edge from-layer="61" from-port="2" to-layer="64" to-port="0" />
		<edge from-layer="62" from-port="0" to-layer="63" to-port="0" />
		<edge from-layer="63" from-port="1" to-layer="64" to-port="1" />
		<edge from-layer="64" from-port="2" to-layer="67" to-port="0" />
		<edge from-layer="65" from-port="0" to-layer="66" to-port="0" />
		<edge from-layer="66" from-port="1" to-layer="67" to-port="1" />
		<edge from-layer="67" from-port="2" to-layer="68" to-port="1" />
		<edge from-layer="68" from-port="2" to-layer="90" to-port="0" />
		<edge from-layer="68" from-port="2" to-layer="70" to-port="0" />
		<edge from-layer="69" from-port="0" to-layer="70" to-port="1" />
		<edge from-layer="70" from-port="2" to-layer="73" to-port="0" />
		<edge from-layer="71" from-port="0" 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="76" to-port="0" />
		<edge from-layer="74" from-port="0" to-layer="75" to-port="0" />
		<edge from-layer="75" from-port="1" to-layer="76" to-port="1" />
		<edge from-layer="76" from-port="2" to-layer="79" to-port="0" />
		<edge from-layer="77" from-port="0" to-layer="78" to-port="0" />
		<edge from-layer="78" from-port="1" to-layer="79" to-port="1" />
		<edge from-layer="79" from-port="2" to-layer="82" to-port="0" />
		<edge from-layer="80" from-port="0" to-layer="81" to-port="0" />
		<edge from-layer="81" from-port="1" to-layer="82" to-port="1" />
		<edge from-layer="82" from-port="2" to-layer="83" to-port="0" />
		<edge from-layer="83" from-port="1" to-layer="86" to-port="0" />
		<edge from-layer="84" from-port="0" to-layer="85" to-port="0" />
		<edge from-layer="85" from-port="1" to-layer="86" to-port="1" />
		<edge from-layer="86" from-port="2" to-layer="89" to-port="0" />
		<edge from-layer="87" from-port="0" to-layer="88" to-port="0" />
		<edge from-layer="88" from-port="1" to-layer="89" to-port="1" />
		<edge from-layer="89" from-port="2" to-layer="90" to-port="1" />
		<edge from-layer="90" from-port="2" to-layer="92" to-port="0" />
		<edge from-layer="90" from-port="2" to-layer="139" to-port="0" />
		<edge from-layer="91" from-port="0" to-layer="92" to-port="1" />
		<edge from-layer="92" from-port="2" to-layer="95" to-port="0" />
		<edge from-layer="93" from-port="0" to-layer="94" to-port="0" />
		<edge from-layer="94" from-port="1" to-layer="95" to-port="1" />
		<edge from-layer="95" from-port="2" to-layer="98" to-port="0" />
		<edge from-layer="96" from-port="0" to-layer="97" to-port="0" />
		<edge from-layer="97" from-port="1" to-layer="98" to-port="1" />
		<edge from-layer="98" from-port="2" to-layer="101" to-port="0" />
		<edge from-layer="98" from-port="2" to-layer="120" to-port="0" />
		<edge from-layer="98" from-port="2" to-layer="111" to-port="0" />
		<edge from-layer="99" from-port="0" to-layer="100" to-port="0" />
		<edge from-layer="100" from-port="1" to-layer="101" to-port="1" />
		<edge from-layer="101" from-port="2" to-layer="104" to-port="0" />
		<edge from-layer="102" from-port="0" to-layer="103" to-port="0" />
		<edge from-layer="103" from-port="1" to-layer="104" to-port="1" />
		<edge from-layer="104" from-port="2" to-layer="106" to-port="0" />
		<edge from-layer="105" from-port="0" to-layer="106" to-port="1" />
		<edge from-layer="106" from-port="2" to-layer="108" to-port="0" />
		<edge from-layer="107" from-port="0" to-layer="108" to-port="1" />
		<edge from-layer="108" from-port="2" to-layer="116" to-port="0" />
		<edge from-layer="109" from-port="0" to-layer="110" to-port="0" />
		<edge from-layer="110" from-port="1" to-layer="111" to-port="1" />
		<edge from-layer="111" from-port="2" to-layer="113" to-port="0" />
		<edge from-layer="112" from-port="0" to-layer="113" to-port="1" />
		<edge from-layer="113" from-port="2" to-layer="115" to-port="0" />
		<edge from-layer="114" from-port="0" to-layer="115" to-port="1" />
		<edge from-layer="115" from-port="2" to-layer="116" to-port="1" />
		<edge from-layer="116" from-port="2" to-layer="117" to-port="0" />
		<edge from-layer="117" from-port="1" to-layer="128" to-port="0" />
		<edge from-layer="118" from-port="0" to-layer="119" to-port="0" />
		<edge from-layer="119" from-port="1" to-layer="120" to-port="1" />
		<edge from-layer="120" from-port="2" to-layer="123" to-port="0" />
		<edge from-layer="121" from-port="0" to-layer="122" to-port="0" />
		<edge from-layer="122" from-port="1" to-layer="123" to-port="1" />
		<edge from-layer="123" from-port="2" to-layer="125" to-port="0" />
		<edge from-layer="124" from-port="0" to-layer="125" to-port="1" />
		<edge from-layer="125" from-port="2" to-layer="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="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="135" to-port="0" />
		<edge from-layer="133" from-port="0" to-layer="134" to-port="0" />
		<edge from-layer="134" from-port="1" to-layer="135" to-port="1" />
		<edge from-layer="135" from-port="2" to-layer="138" to-port="0" />
		<edge from-layer="136" from-port="0" to-layer="137" to-port="0" />
		<edge from-layer="137" from-port="1" to-layer="138" to-port="1" />
		<edge from-layer="138" from-port="2" to-layer="139" to-port="1" />
		<edge from-layer="139" from-port="2" to-layer="161" to-port="0" />
		<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="144" to-port="0" />
		<edge from-layer="142" from-port="0" to-layer="143" to-port="0" />
		<edge from-layer="143" from-port="1" to-layer="144" to-port="1" />
		<edge from-layer="144" from-port="2" to-layer="147" to-port="0" />
		<edge from-layer="145" from-port="0" to-layer="146" to-port="0" />
		<edge from-layer="146" from-port="1" to-layer="147" to-port="1" />
		<edge from-layer="147" from-port="2" to-layer="150" to-port="0" />
		<edge from-layer="148" from-port="0" to-layer="149" to-port="0" />
		<edge from-layer="149" from-port="1" to-layer="150" to-port="1" />
		<edge from-layer="150" from-port="2" to-layer="153" to-port="0" />
		<edge from-layer="151" from-port="0" to-layer="152" to-port="0" />
		<edge from-layer="152" from-port="1" to-layer="153" to-port="1" />
		<edge from-layer="153" from-port="2" to-layer="154" to-port="0" />
		<edge from-layer="154" from-port="1" to-layer="157" to-port="0" />
		<edge from-layer="155" from-port="0" to-layer="156" to-port="0" />
		<edge from-layer="156" from-port="1" to-layer="157" to-port="1" />
		<edge from-layer="157" from-port="2" to-layer="160" to-port="0" />
		<edge from-layer="158" from-port="0" to-layer="159" to-port="0" />
		<edge from-layer="159" from-port="1" to-layer="160" to-port="1" />
		<edge from-layer="160" from-port="2" to-layer="161" to-port="1" />
		<edge from-layer="161" from-port="2" to-layer="210" to-port="0" />
		<edge from-layer="161" from-port="2" to-layer="163" to-port="0" />
		<edge from-layer="162" from-port="0" to-layer="163" to-port="1" />
		<edge from-layer="163" from-port="2" to-layer="166" to-port="0" />
		<edge from-layer="164" from-port="0" to-layer="165" to-port="0" />
		<edge from-layer="165" from-port="1" to-layer="166" to-port="1" />
		<edge from-layer="166" from-port="2" to-layer="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="172" to-port="0" />
		<edge from-layer="169" from-port="2" to-layer="191" to-port="0" />
		<edge from-layer="169" from-port="2" to-layer="182" to-port="0" />
		<edge from-layer="170" from-port="0" to-layer="171" to-port="0" />
		<edge from-layer="171" from-port="1" to-layer="172" to-port="1" />
		<edge from-layer="172" from-port="2" to-layer="175" to-port="0" />
		<edge from-layer="173" from-port="0" to-layer="174" to-port="0" />
		<edge from-layer="174" from-port="1" 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="187" to-port="0" />
		<edge from-layer="180" from-port="0" to-layer="181" to-port="0" />
		<edge from-layer="181" from-port="1" to-layer="182" to-port="1" />
		<edge from-layer="182" from-port="2" to-layer="184" to-port="0" />
		<edge from-layer="183" from-port="0" to-layer="184" to-port="1" />
		<edge from-layer="184" from-port="2" to-layer="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="187" to-port="1" />
		<edge from-layer="187" from-port="2" to-layer="188" to-port="0" />
		<edge from-layer="188" from-port="1" to-layer="199" 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="194" to-port="0" />
		<edge from-layer="192" from-port="0" to-layer="193" to-port="0" />
		<edge from-layer="193" from-port="1" to-layer="194" to-port="1" />
		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
		<edge from-layer="195" from-port="0" to-layer="196" to-port="1" />
		<edge from-layer="196" from-port="2" to-layer="198" to-port="0" />
		<edge from-layer="197" from-port="0" to-layer="198" to-port="1" />
		<edge from-layer="198" from-port="2" to-layer="199" to-port="1" />
		<edge from-layer="199" from-port="2" to-layer="201" to-port="0" />
		<edge from-layer="200" from-port="0" to-layer="201" to-port="1" />
		<edge from-layer="201" from-port="2" to-layer="203" to-port="0" />
		<edge from-layer="202" from-port="0" to-layer="203" to-port="1" />
		<edge from-layer="203" from-port="2" to-layer="206" to-port="0" />
		<edge from-layer="204" from-port="0" to-layer="205" to-port="0" />
		<edge from-layer="205" from-port="1" to-layer="206" to-port="1" />
		<edge from-layer="206" from-port="2" to-layer="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="210" to-port="1" />
		<edge from-layer="210" from-port="2" to-layer="232" to-port="0" />
		<edge from-layer="210" from-port="2" to-layer="212" to-port="0" />
		<edge from-layer="211" from-port="0" to-layer="212" to-port="1" />
		<edge from-layer="212" from-port="2" to-layer="215" to-port="0" />
		<edge from-layer="213" from-port="0" to-layer="214" to-port="0" />
		<edge from-layer="214" from-port="1" to-layer="215" to-port="1" />
		<edge from-layer="215" from-port="2" to-layer="218" to-port="0" />
		<edge from-layer="216" from-port="0" to-layer="217" to-port="0" />
		<edge from-layer="217" from-port="1" to-layer="218" to-port="1" />
		<edge from-layer="218" from-port="2" 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="224" to-port="0" />
		<edge from-layer="222" from-port="0" to-layer="223" to-port="0" />
		<edge from-layer="223" from-port="1" to-layer="224" to-port="1" />
		<edge from-layer="224" from-port="2" to-layer="225" to-port="0" />
		<edge from-layer="225" from-port="1" to-layer="228" to-port="0" />
		<edge from-layer="226" from-port="0" to-layer="227" to-port="0" />
		<edge from-layer="227" from-port="1" to-layer="228" to-port="1" />
		<edge from-layer="228" from-port="2" to-layer="231" to-port="0" />
		<edge from-layer="229" from-port="0" to-layer="230" to-port="0" />
		<edge from-layer="230" from-port="1" to-layer="231" to-port="1" />
		<edge from-layer="231" from-port="2" to-layer="232" to-port="1" />
		<edge from-layer="232" from-port="2" to-layer="234" to-port="0" />
		<edge from-layer="232" from-port="2" to-layer="281" 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="237" 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="237" to-port="1" />
		<edge from-layer="237" from-port="2" to-layer="240" to-port="0" />
		<edge from-layer="238" from-port="0" to-layer="239" to-port="0" />
		<edge from-layer="239" from-port="1" to-layer="240" to-port="1" />
		<edge from-layer="240" from-port="2" to-layer="253" to-port="0" />
		<edge from-layer="240" from-port="2" to-layer="262" to-port="0" />
		<edge from-layer="240" from-port="2" to-layer="243" to-port="0" />
		<edge from-layer="241" from-port="0" 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="246" to-port="0" />
		<edge from-layer="244" from-port="0" to-layer="245" to-port="0" />
		<edge from-layer="245" from-port="1" to-layer="246" to-port="1" />
		<edge from-layer="246" from-port="2" to-layer="248" to-port="0" />
		<edge from-layer="247" from-port="0" to-layer="248" to-port="1" />
		<edge from-layer="248" from-port="2" to-layer="250" to-port="0" />
		<edge from-layer="249" from-port="0" to-layer="250" to-port="1" />
		<edge from-layer="250" from-port="2" to-layer="258" to-port="0" />
		<edge from-layer="251" from-port="0" to-layer="252" to-port="0" />
		<edge from-layer="252" from-port="1" to-layer="253" to-port="1" />
		<edge from-layer="253" from-port="2" to-layer="255" to-port="0" />
		<edge from-layer="254" from-port="0" to-layer="255" to-port="1" />
		<edge from-layer="255" from-port="2" to-layer="257" to-port="0" />
		<edge from-layer="256" from-port="0" to-layer="257" to-port="1" />
		<edge from-layer="257" from-port="2" 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="270" to-port="0" />
		<edge from-layer="260" from-port="0" to-layer="261" to-port="0" />
		<edge from-layer="261" from-port="1" to-layer="262" to-port="1" />
		<edge from-layer="262" from-port="2" to-layer="265" to-port="0" />
		<edge from-layer="263" from-port="0" to-layer="264" to-port="0" />
		<edge from-layer="264" from-port="1" to-layer="265" to-port="1" />
		<edge from-layer="265" from-port="2" to-layer="267" to-port="0" />
		<edge from-layer="266" from-port="0" to-layer="267" to-port="1" />
		<edge from-layer="267" from-port="2" to-layer="269" to-port="0" />
		<edge from-layer="268" from-port="0" to-layer="269" to-port="1" />
		<edge from-layer="269" from-port="2" to-layer="270" to-port="1" />
		<edge from-layer="270" from-port="2" to-layer="272" to-port="0" />
		<edge from-layer="271" from-port="0" to-layer="272" to-port="1" />
		<edge from-layer="272" from-port="2" to-layer="274" to-port="0" />
		<edge from-layer="273" from-port="0" to-layer="274" to-port="1" />
		<edge from-layer="274" from-port="2" to-layer="277" to-port="0" />
		<edge from-layer="275" from-port="0" to-layer="276" to-port="0" />
		<edge from-layer="276" from-port="1" to-layer="277" to-port="1" />
		<edge from-layer="277" from-port="2" to-layer="280" to-port="0" />
		<edge from-layer="278" from-port="0" to-layer="279" to-port="0" />
		<edge from-layer="279" from-port="1" to-layer="280" to-port="1" />
		<edge from-layer="280" from-port="2" to-layer="281" to-port="1" />
		<edge from-layer="281" from-port="2" to-layer="303" to-port="0" />
		<edge from-layer="281" from-port="2" to-layer="283" to-port="0" />
		<edge from-layer="282" from-port="0" to-layer="283" to-port="1" />
		<edge from-layer="283" from-port="2" to-layer="286" to-port="0" />
		<edge from-layer="284" from-port="0" to-layer="285" to-port="0" />
		<edge from-layer="285" from-port="1" to-layer="286" to-port="1" />
		<edge from-layer="286" from-port="2" to-layer="289" 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="289" to-port="1" />
		<edge from-layer="289" from-port="2" to-layer="292" to-port="0" />
		<edge from-layer="290" from-port="0" to-layer="291" to-port="0" />
		<edge from-layer="291" from-port="1" to-layer="292" to-port="1" />
		<edge from-layer="292" from-port="2" to-layer="295" to-port="0" />
		<edge from-layer="293" from-port="0" to-layer="294" to-port="0" />
		<edge from-layer="294" from-port="1" to-layer="295" to-port="1" />
		<edge from-layer="295" from-port="2" to-layer="296" to-port="0" />
		<edge from-layer="296" from-port="1" to-layer="299" to-port="0" />
		<edge from-layer="297" from-port="0" to-layer="298" to-port="0" />
		<edge from-layer="298" from-port="1" to-layer="299" to-port="1" />
		<edge from-layer="299" from-port="2" to-layer="302" to-port="0" />
		<edge from-layer="300" from-port="0" to-layer="301" to-port="0" />
		<edge from-layer="301" from-port="1" to-layer="302" to-port="1" />
		<edge from-layer="302" from-port="2" to-layer="303" to-port="1" />
		<edge from-layer="303" from-port="2" to-layer="305" to-port="0" />
		<edge from-layer="304" from-port="0" to-layer="305" to-port="1" />
		<edge from-layer="305" from-port="2" to-layer="308" to-port="0" />
		<edge from-layer="306" from-port="0" to-layer="307" to-port="0" />
		<edge from-layer="307" from-port="1" to-layer="308" to-port="1" />
		<edge from-layer="308" from-port="2" to-layer="311" to-port="0" />
		<edge from-layer="309" from-port="0" to-layer="310" to-port="0" />
		<edge from-layer="310" from-port="1" to-layer="311" to-port="1" />
		<edge from-layer="311" from-port="2" to-layer="312" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2024.5.0-16901-32aaa2fbd96" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<optimum>
			<optimum_intel_version value="1.20.0.dev0+2559620" />
			<optimum_version value="1.23.1" />
			<pytorch_version value="2.5.0" />
			<transformers_version value="4.45.2" />
		</optimum>
	</rt_info>
</net>