openvino/openvino_model.xml

<?xml version="1.0"?>
<net name="Model0" version="11">
	<layers>
		<layer id="1" name="input_ids" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="input_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="0" name="attention_mask" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="attention_mask">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="Constant_12950" type="Const" version="opset1">
			<data element_type="i64" shape="1, 1" offset="0" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="__module.transformer.layer.0.attention/aten::eq/Equal" type="Equal" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="165,235,305,375,445,95">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="__module.embeddings.word_embeddings/aten::embedding/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="ShapeOf_13125" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="Constant_13131" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="0" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="Constant_13132" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="0" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="8" name="Gather_13133" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="142,212,282,352,422,72">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="__module.transformer.layer.0.attention/prim::ListConstruct/Reshape_0" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="8" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="self.embeddings.word_embeddings.weight" type="Const" version="opset1">
			<data element_type="f32" shape="119547, 768" offset="16" size="367248384" />
			<output>
				<port id="0" precision="FP32" names="self.embeddings.word_embeddings.weight">
					<dim>119547</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="__module.embeddings.word_embeddings/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="367248400" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="12" name="__module.embeddings.word_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>119547</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="22,input_embeds">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="self.embeddings.position_embeddings.weight" type="Const" version="opset1">
			<data element_type="f32" shape="512, 768" offset="367248404" size="1572864" />
			<output>
				<port id="0" precision="FP32" names="self.embeddings.position_embeddings.weight">
					<dim>512</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="__module.embeddings/aten::slice/Slice" type="Const" version="opset1">
			<data element_type="i64" shape="1, 512" offset="368821268" size="4096" />
			<output>
				<port id="0" precision="I64" names="24">
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="__module.embeddings/aten::slice/Reshape" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="0" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="Constant_13126" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="8" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="Constant_13127" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="0" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="18" name="Gather_13128" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="23">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="__module.embeddings/aten::slice/Reshape_2" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="8" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="20" name="__module.embeddings/aten::slice/Reshape_3" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="8" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="21" name="__module.embeddings/aten::slice/Slice_1" type="Slice" version="opset8">
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
				<port id="4" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="5" precision="I64" names="25">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="__module.embeddings.position_embeddings/aten::embedding/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="__module.embeddings.position_embeddings/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="367248400" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="24" name="__module.embeddings.position_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>512</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="27,position_embeddings.1">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="__module.embeddings/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="28">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="26" name="__module.embeddings.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="27" name="__module.embeddings.LayerNorm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="Constant_12951" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="368825368" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="29" name="__module.embeddings.LayerNorm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="Constant_12952" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="368828440" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="31" name="__module.embeddings.LayerNorm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="32,input.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="ShapeOf_13135" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="Constant_13136" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="8" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="Constant_13137" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="0" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="35" name="Gather_13138" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="143,213,283,353,423,73">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="__module.transformer.layer.0.attention/prim::ListConstruct/Concat" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="I64" names="166,236,306,376,446,96">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="__module.transformer.layer.0.attention/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="167,237,307,377,447,97">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="self.transformer.layer.0.attention.q_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="368831512" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.0.attention.q_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="__module.transformer.layer.0.attention.q_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="Constant_12953" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="371190808" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="__module.transformer.layer.0.attention.q_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="76,x.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="Constant_13140" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="__module.transformer.layer.0.attention/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="78">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="__module.transformer.layer.0.attention/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="__module.transformer.layer.0.attention/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="79,q.1">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="Constant_12954" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="371193928" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="__module.transformer.layer.0.attention/aten::div/Divide" type="Divide" version="opset1">
			<data auto_broadcast="numpy" m_pythondiv="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="92">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="self.transformer.layer.0.attention.k_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="371193932" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.0.attention.k_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="__module.transformer.layer.0.attention.k_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="Constant_12955" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="373553228" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="__module.transformer.layer.0.attention.k_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="82,x.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="Constant_13141" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="__module.transformer.layer.0.attention/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="84">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="Constant_12664" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="373556300" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="__module.transformer.layer.0.attention/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="93">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="__module.transformer.layer.0.attention/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="94,scores.1">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="__module.transformer.layer.0.attention/aten::expand_as/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="__module.transformer.layer.0.attention/aten::expand_as/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="98,mask.1">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="__module.transformer.layer.0.attention/aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="373556316" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="60" name="__module.transformer.layer.0.attention/aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="101,input.3">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="__module.transformer.layer.0.attention/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="102,input.5">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="self.transformer.layer.0.attention.v_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="373556320" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.0.attention.v_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="__module.transformer.layer.0.attention.v_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="Constant_12956" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="375915616" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="__module.transformer.layer.0.attention.v_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="88,x.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Constant_13142" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="__module.transformer.layer.0.attention/aten::view/Reshape_3" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="90">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="__module.transformer.layer.0.attention/aten::transpose/ScatterElementsUpdate_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="__module.transformer.layer.0.attention/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="91">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="70" name="__module.transformer.layer.0.attention/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>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="104,x.7">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="__module.transformer.layer.0.attention/aten::transpose/ScatterElementsUpdate_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="__module.transformer.layer.0.attention/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="105">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="73" name="Constant_13143" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="375918688" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="__module.transformer.layer.0.attention/aten::view/Reshape_4" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="108">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="self.transformer.layer.0.attention.out_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="375918712" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.0.attention.out_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="__module.transformer.layer.0.attention.out_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="Constant_12957" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="378278008" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="__module.transformer.layer.0.attention.out_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="111,sa_output.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.transformer.layer.0/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="112">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="__module.transformer.layer.0.sa_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="__module.transformer.layer.0.sa_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="82" name="Constant_12958" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="378281080" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="__module.transformer.layer.0.sa_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="Constant_12959" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="378284152" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="__module.transformer.layer.0.sa_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="116,sa_output.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="self.transformer.layer.0.ffn.lin1.weight" type="Const" version="opset1">
			<data element_type="f32" shape="3072, 768" offset="378287224" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.0.ffn.lin1.weight">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="__module.transformer.layer.0.ffn.lin1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="Constant_12960" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 3072" offset="387724408" size="12288" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.transformer.layer.0.ffn.lin1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="123">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="__module.transformer.layer.0.ffn.activation/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="124">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="self.transformer.layer.0.ffn.lin2.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 3072" offset="387736696" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.0.ffn.lin2.weight">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="__module.transformer.layer.0.ffn.lin2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="Constant_12961" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="397173880" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="__module.transformer.layer.0.ffn.lin2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="127,input.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="__module.transformer.layer.0/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="129">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="__module.transformer.layer.0.output_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="__module.transformer.layer.0.output_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="Constant_12962" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="397176952" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="__module.transformer.layer.0.output_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="Constant_12963" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="397180024" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="__module.transformer.layer.0.output_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="133,query.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="self.transformer.layer.1.attention.q_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="397183096" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.1.attention.q_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="__module.transformer.layer.1.attention.q_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="Constant_12964" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="399542392" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="__module.transformer.layer.1.attention.q_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="146,x.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="Constant_13144" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="__module.transformer.layer.1.attention/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="148">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="__module.transformer.layer.1.attention/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="__module.transformer.layer.1.attention/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="149,q.3">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="Constant_12965" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="371193928" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="__module.transformer.layer.1.attention/aten::div/Divide" type="Divide" version="opset1">
			<data auto_broadcast="numpy" m_pythondiv="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="162">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="self.transformer.layer.1.attention.k_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="399545464" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.1.attention.k_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="__module.transformer.layer.1.attention.k_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="Constant_12966" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="401904760" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="__module.transformer.layer.1.attention.k_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="152,x.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="Constant_13145" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="__module.transformer.layer.1.attention/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="154">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="Constant_12666" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="373556300" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="__module.transformer.layer.1.attention/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="163">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="__module.transformer.layer.1.attention/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="164,scores.3">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="__module.transformer.layer.1.attention/aten::expand_as/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="__module.transformer.layer.1.attention/aten::expand_as/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="168,mask.3">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="__module.transformer.layer.1.attention/aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="373556316" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="124" name="__module.transformer.layer.1.attention/aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="171,input.9">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="__module.transformer.layer.1.attention/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="172,input.11">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="self.transformer.layer.1.attention.v_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="401907832" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.1.attention.v_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="__module.transformer.layer.1.attention.v_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="Constant_12967" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="404267128" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="__module.transformer.layer.1.attention.v_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="158,x.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="Constant_13146" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="__module.transformer.layer.1.attention/aten::view/Reshape_3" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="160">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="__module.transformer.layer.1.attention/aten::transpose/ScatterElementsUpdate_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="__module.transformer.layer.1.attention/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="161">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="__module.transformer.layer.1.attention/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>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="174,x.15">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="135" name="__module.transformer.layer.1.attention/aten::transpose/ScatterElementsUpdate_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="__module.transformer.layer.1.attention/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="175">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="Constant_13147" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="375918688" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="__module.transformer.layer.1.attention/aten::view/Reshape_4" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="178">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="self.transformer.layer.1.attention.out_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="404270200" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.1.attention.out_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="__module.transformer.layer.1.attention.out_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="Constant_12968" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="406629496" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="__module.transformer.layer.1.attention.out_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="181,sa_output.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="__module.transformer.layer.1/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="182">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="__module.transformer.layer.1.sa_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="__module.transformer.layer.1.sa_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="Constant_12969" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="406632568" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="__module.transformer.layer.1.sa_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="Constant_12970" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="406635640" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="__module.transformer.layer.1.sa_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="186,sa_output.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="self.transformer.layer.1.ffn.lin1.weight" type="Const" version="opset1">
			<data element_type="f32" shape="3072, 768" offset="406638712" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.1.ffn.lin1.weight">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="__module.transformer.layer.1.ffn.lin1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="Constant_12971" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 3072" offset="416075896" size="12288" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="__module.transformer.layer.1.ffn.lin1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="193">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="__module.transformer.layer.1.ffn.activation/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="194">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="self.transformer.layer.1.ffn.lin2.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 3072" offset="416088184" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.1.ffn.lin2.weight">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="__module.transformer.layer.1.ffn.lin2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="Constant_12972" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="425525368" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="__module.transformer.layer.1.ffn.lin2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="197,input.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="159" name="__module.transformer.layer.1/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="199">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="__module.transformer.layer.1.output_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="__module.transformer.layer.1.output_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="Constant_12973" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="425528440" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="__module.transformer.layer.1.output_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="Constant_12974" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="425531512" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="__module.transformer.layer.1.output_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="203,query.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="self.transformer.layer.2.attention.q_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="425534584" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.2.attention.q_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="__module.transformer.layer.2.attention.q_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="168" name="Constant_12975" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="427893880" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="__module.transformer.layer.2.attention.q_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="216,x.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="Constant_13148" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="171" name="__module.transformer.layer.2.attention/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="218">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="__module.transformer.layer.2.attention/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="__module.transformer.layer.2.attention/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="219,q.5">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="Constant_12976" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="371193928" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="__module.transformer.layer.2.attention/aten::div/Divide" type="Divide" version="opset1">
			<data auto_broadcast="numpy" m_pythondiv="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="232">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="self.transformer.layer.2.attention.k_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="427896952" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.2.attention.k_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="177" name="__module.transformer.layer.2.attention.k_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="Constant_12977" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="430256248" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="__module.transformer.layer.2.attention.k_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="222,x.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="180" name="Constant_13149" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="181" name="__module.transformer.layer.2.attention/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="224">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="Constant_12668" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="373556300" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="__module.transformer.layer.2.attention/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="233">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="__module.transformer.layer.2.attention/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="234,scores.5">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="__module.transformer.layer.2.attention/aten::expand_as/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="__module.transformer.layer.2.attention/aten::expand_as/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="238,mask.5">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="__module.transformer.layer.2.attention/aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="373556316" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="188" name="__module.transformer.layer.2.attention/aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="241,input.15">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="__module.transformer.layer.2.attention/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="242,input.17">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="self.transformer.layer.2.attention.v_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="430259320" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.2.attention.v_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="__module.transformer.layer.2.attention.v_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="Constant_12978" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="432618616" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="193" name="__module.transformer.layer.2.attention.v_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="228,x.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="Constant_13150" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="__module.transformer.layer.2.attention/aten::view/Reshape_3" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="230">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="196" name="__module.transformer.layer.2.attention/aten::transpose/ScatterElementsUpdate_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.transformer.layer.2.attention/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="231">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="198" name="__module.transformer.layer.2.attention/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>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="244,x.23">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.transformer.layer.2.attention/aten::transpose/ScatterElementsUpdate_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="__module.transformer.layer.2.attention/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="245">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="201" name="Constant_13151" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="375918688" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="__module.transformer.layer.2.attention/aten::view/Reshape_4" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="248">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="203" name="self.transformer.layer.2.attention.out_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="432621688" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.2.attention.out_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="__module.transformer.layer.2.attention.out_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="Constant_12979" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="434980984" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="__module.transformer.layer.2.attention.out_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="251,sa_output.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="__module.transformer.layer.2/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="252">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="__module.transformer.layer.2.sa_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="__module.transformer.layer.2.sa_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="Constant_12980" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="434984056" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="__module.transformer.layer.2.sa_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="Constant_12981" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="434987128" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="__module.transformer.layer.2.sa_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="256,sa_output.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="214" name="self.transformer.layer.2.ffn.lin1.weight" type="Const" version="opset1">
			<data element_type="f32" shape="3072, 768" offset="434990200" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.2.ffn.lin1.weight">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="__module.transformer.layer.2.ffn.lin1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="Constant_12982" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 3072" offset="444427384" size="12288" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="217" name="__module.transformer.layer.2.ffn.lin1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="263">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="218" name="__module.transformer.layer.2.ffn.activation/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="264">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="219" name="self.transformer.layer.2.ffn.lin2.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 3072" offset="444439672" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.2.ffn.lin2.weight">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="__module.transformer.layer.2.ffn.lin2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="221" name="Constant_12983" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="453876856" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="222" name="__module.transformer.layer.2.ffn.lin2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="267,input.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="__module.transformer.layer.2/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="269">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="__module.transformer.layer.2.output_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="__module.transformer.layer.2.output_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="Constant_12984" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="453879928" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="__module.transformer.layer.2.output_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="Constant_12985" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="453883000" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="__module.transformer.layer.2.output_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="273,query.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="230" name="self.transformer.layer.3.attention.q_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="453886072" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.3.attention.q_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="__module.transformer.layer.3.attention.q_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="Constant_12986" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="456245368" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="233" name="__module.transformer.layer.3.attention.q_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="286,x.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="Constant_13152" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="235" name="__module.transformer.layer.3.attention/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="288">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="236" name="__module.transformer.layer.3.attention/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="__module.transformer.layer.3.attention/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="289,q.7">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="Constant_12987" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="371193928" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="239" name="__module.transformer.layer.3.attention/aten::div/Divide" type="Divide" version="opset1">
			<data auto_broadcast="numpy" m_pythondiv="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="302">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="self.transformer.layer.3.attention.k_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="456248440" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.3.attention.k_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="__module.transformer.layer.3.attention.k_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="242" name="Constant_12988" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="458607736" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="__module.transformer.layer.3.attention.k_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="292,x.27">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="244" name="Constant_13153" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="__module.transformer.layer.3.attention/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="294">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="Constant_12670" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="373556300" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="247" name="__module.transformer.layer.3.attention/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="303">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="248" name="__module.transformer.layer.3.attention/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="304,scores.7">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="249" name="__module.transformer.layer.3.attention/aten::expand_as/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="250" name="__module.transformer.layer.3.attention/aten::expand_as/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="308,mask.7">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="__module.transformer.layer.3.attention/aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="373556316" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="252" name="__module.transformer.layer.3.attention/aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="311,input.21">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="253" name="__module.transformer.layer.3.attention/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="312,input.23">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="254" name="self.transformer.layer.3.attention.v_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="458610808" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.3.attention.v_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="__module.transformer.layer.3.attention.v_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="256" name="Constant_12989" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="460970104" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="257" name="__module.transformer.layer.3.attention.v_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="298,x.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="258" name="Constant_13154" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="259" name="__module.transformer.layer.3.attention/aten::view/Reshape_3" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="300">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="__module.transformer.layer.3.attention/aten::transpose/ScatterElementsUpdate_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="__module.transformer.layer.3.attention/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="301">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="__module.transformer.layer.3.attention/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>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="314,x.31">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="__module.transformer.layer.3.attention/aten::transpose/ScatterElementsUpdate_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="__module.transformer.layer.3.attention/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="315">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="Constant_13155" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="375918688" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="__module.transformer.layer.3.attention/aten::view/Reshape_4" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="318">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="self.transformer.layer.3.attention.out_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="460973176" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.3.attention.out_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="__module.transformer.layer.3.attention.out_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="269" name="Constant_12990" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="463332472" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="__module.transformer.layer.3.attention.out_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="321,sa_output.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="__module.transformer.layer.3/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="322">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="272" name="__module.transformer.layer.3.sa_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="__module.transformer.layer.3.sa_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="Constant_12991" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="463335544" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="__module.transformer.layer.3.sa_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="Constant_12992" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="463338616" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="__module.transformer.layer.3.sa_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="326,sa_output.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="self.transformer.layer.3.ffn.lin1.weight" type="Const" version="opset1">
			<data element_type="f32" shape="3072, 768" offset="463341688" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.3.ffn.lin1.weight">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="__module.transformer.layer.3.ffn.lin1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="Constant_12993" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 3072" offset="472778872" size="12288" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="281" name="__module.transformer.layer.3.ffn.lin1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="333">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="__module.transformer.layer.3.ffn.activation/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="334">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="self.transformer.layer.3.ffn.lin2.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 3072" offset="472791160" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.3.ffn.lin2.weight">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="__module.transformer.layer.3.ffn.lin2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="Constant_12994" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="482228344" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="__module.transformer.layer.3.ffn.lin2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="337,input.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="287" name="__module.transformer.layer.3/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="339">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="__module.transformer.layer.3.output_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="289" name="__module.transformer.layer.3.output_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="Constant_12995" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="482231416" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="__module.transformer.layer.3.output_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="Constant_12996" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="482234488" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="__module.transformer.layer.3.output_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="343,query.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="self.transformer.layer.4.attention.q_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="482237560" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.4.attention.q_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="__module.transformer.layer.4.attention.q_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="Constant_12997" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="484596856" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="__module.transformer.layer.4.attention.q_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="356,x.33">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="Constant_13156" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="__module.transformer.layer.4.attention/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="358">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="__module.transformer.layer.4.attention/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="301" name="__module.transformer.layer.4.attention/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="359,q.9">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="Constant_12998" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="371193928" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="__module.transformer.layer.4.attention/aten::div/Divide" type="Divide" version="opset1">
			<data auto_broadcast="numpy" m_pythondiv="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="372">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="self.transformer.layer.4.attention.k_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="484599928" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.4.attention.k_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="305" name="__module.transformer.layer.4.attention.k_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="Constant_12999" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="486959224" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="__module.transformer.layer.4.attention.k_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="362,x.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="Constant_13157" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="__module.transformer.layer.4.attention/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="364">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="Constant_12672" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="373556300" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="__module.transformer.layer.4.attention/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="373">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="__module.transformer.layer.4.attention/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="374,scores.9">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="313" name="__module.transformer.layer.4.attention/aten::expand_as/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="__module.transformer.layer.4.attention/aten::expand_as/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="378,mask.9">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="__module.transformer.layer.4.attention/aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="373556316" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="316" name="__module.transformer.layer.4.attention/aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="381,input.27">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="__module.transformer.layer.4.attention/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="382,input.29">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="self.transformer.layer.4.attention.v_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="486962296" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.4.attention.v_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="319" name="__module.transformer.layer.4.attention.v_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="320" name="Constant_13000" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="489321592" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="__module.transformer.layer.4.attention.v_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="368,x.37">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="Constant_13158" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="323" name="__module.transformer.layer.4.attention/aten::view/Reshape_3" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="370">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="324" name="__module.transformer.layer.4.attention/aten::transpose/ScatterElementsUpdate_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="325" name="__module.transformer.layer.4.attention/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="371">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="326" name="__module.transformer.layer.4.attention/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>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="384,x.39">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="327" name="__module.transformer.layer.4.attention/aten::transpose/ScatterElementsUpdate_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="328" name="__module.transformer.layer.4.attention/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="385">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="329" name="Constant_13159" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="375918688" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="330" name="__module.transformer.layer.4.attention/aten::view/Reshape_4" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="388">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="331" name="self.transformer.layer.4.attention.out_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="489324664" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.4.attention.out_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="332" name="__module.transformer.layer.4.attention.out_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="333" name="Constant_13001" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="491683960" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="__module.transformer.layer.4.attention.out_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="391,sa_output.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="335" name="__module.transformer.layer.4/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="392">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="__module.transformer.layer.4.sa_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="__module.transformer.layer.4.sa_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="338" name="Constant_13002" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="491687032" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="__module.transformer.layer.4.sa_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="Constant_13003" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="491690104" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="__module.transformer.layer.4.sa_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="396,sa_output.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="self.transformer.layer.4.ffn.lin1.weight" type="Const" version="opset1">
			<data element_type="f32" shape="3072, 768" offset="491693176" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.4.ffn.lin1.weight">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="__module.transformer.layer.4.ffn.lin1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="344" name="Constant_13004" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 3072" offset="501130360" size="12288" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="345" name="__module.transformer.layer.4.ffn.lin1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="403">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="346" name="__module.transformer.layer.4.ffn.activation/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="404">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="self.transformer.layer.4.ffn.lin2.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 3072" offset="501142648" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.4.ffn.lin2.weight">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="348" name="__module.transformer.layer.4.ffn.lin2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="Constant_13005" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="510579832" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="350" name="__module.transformer.layer.4.ffn.lin2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="407,input.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="351" name="__module.transformer.layer.4/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="409">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="__module.transformer.layer.4.output_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="353" name="__module.transformer.layer.4.output_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="Constant_13006" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="510582904" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="355" name="__module.transformer.layer.4.output_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="Constant_13007" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="510585976" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="__module.transformer.layer.4.output_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="413,query">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="358" name="self.transformer.layer.5.attention.q_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="510589048" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.5.attention.q_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="__module.transformer.layer.5.attention.q_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="Constant_13008" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="512948344" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="361" name="__module.transformer.layer.5.attention.q_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="426,x.41">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="362" name="Constant_13160" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="363" name="__module.transformer.layer.5.attention/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="428">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="__module.transformer.layer.5.attention/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="365" name="__module.transformer.layer.5.attention/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="429,q">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="366" name="Constant_13009" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="371193928" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="367" name="__module.transformer.layer.5.attention/aten::div/Divide" type="Divide" version="opset1">
			<data auto_broadcast="numpy" m_pythondiv="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="442">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="368" name="self.transformer.layer.5.attention.k_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="512951416" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.5.attention.k_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="369" name="__module.transformer.layer.5.attention.k_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="370" name="Constant_13010" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="515310712" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="371" name="__module.transformer.layer.5.attention.k_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="432,x.43">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="372" name="Constant_13161" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="373" name="__module.transformer.layer.5.attention/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="434">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="374" name="Constant_12674" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="373556300" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="375" name="__module.transformer.layer.5.attention/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="443">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="376" name="__module.transformer.layer.5.attention/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="444,scores">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="377" name="__module.transformer.layer.5.attention/aten::expand_as/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="378" name="__module.transformer.layer.5.attention/aten::expand_as/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="448,mask">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="379" name="__module.transformer.layer.5.attention/aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="373556316" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="380" name="__module.transformer.layer.5.attention/aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="451,input.33">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="381" name="__module.transformer.layer.5.attention/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="452,input.35">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="382" name="self.transformer.layer.5.attention.v_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="515313784" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.5.attention.v_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="383" name="__module.transformer.layer.5.attention.v_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="384" name="Constant_13011" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="517673080" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="385" name="__module.transformer.layer.5.attention.v_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="438,x.45">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="386" name="Constant_13162" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="371193880" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="387" name="__module.transformer.layer.5.attention/aten::view/Reshape_3" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="440">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="388" name="__module.transformer.layer.5.attention/aten::transpose/ScatterElementsUpdate_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="389" name="__module.transformer.layer.5.attention/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="441">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="390" name="__module.transformer.layer.5.attention/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>12</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="454,x">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="391" name="__module.transformer.layer.5.attention/aten::transpose/ScatterElementsUpdate_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="371193912" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="392" name="__module.transformer.layer.5.attention/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>12</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="455">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="393" name="Constant_13163" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="375918688" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="394" name="__module.transformer.layer.5.attention/aten::view/Reshape_4" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>12</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="458">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="395" name="self.transformer.layer.5.attention.out_lin.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 768" offset="517676152" size="2359296" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.5.attention.out_lin.weight">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="396" name="__module.transformer.layer.5.attention.out_lin/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="397" name="Constant_13012" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="520035448" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="398" name="__module.transformer.layer.5.attention.out_lin/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="461,sa_output.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="399" name="__module.transformer.layer.5/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="462">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="400" name="__module.transformer.layer.5.sa_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="401" name="__module.transformer.layer.5.sa_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="402" name="Constant_13013" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="520038520" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="403" name="__module.transformer.layer.5.sa_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="404" name="Constant_13014" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="520041592" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="405" name="__module.transformer.layer.5.sa_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="466,sa_output">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="406" name="self.transformer.layer.5.ffn.lin1.weight" type="Const" version="opset1">
			<data element_type="f32" shape="3072, 768" offset="520044664" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.5.ffn.lin1.weight">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="407" name="__module.transformer.layer.5.ffn.lin1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>3072</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="408" name="Constant_13015" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 3072" offset="529481848" size="12288" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="409" name="__module.transformer.layer.5.ffn.lin1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="473">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="410" name="__module.transformer.layer.5.ffn.activation/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="474">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="411" name="self.transformer.layer.5.ffn.lin2.weight" type="Const" version="opset1">
			<data element_type="f32" shape="768, 3072" offset="529494136" size="9437184" />
			<output>
				<port id="0" precision="FP32" names="self.transformer.layer.5.ffn.lin2.weight">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</output>
		</layer>
		<layer id="412" name="__module.transformer.layer.5.ffn.lin2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>3072</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>768</dim>
					<dim>3072</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="413" name="Constant_13016" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="538931320" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="414" name="__module.transformer.layer.5.ffn.lin2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="477,input">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="415" name="__module.transformer.layer.5/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="479">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="416" name="__module.transformer.layer.5.output_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="368825364" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="417" name="__module.transformer.layer.5.output_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.999999960041972e-13" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="418" name="Constant_13017" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="538934392" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="419" name="__module.transformer.layer.5.output_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="420" name="Constant_13018" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 768" offset="538937464" size="3072" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="421" name="__module.transformer.layer.5.output_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="last_hidden_state">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="422" name="Result_3729" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>768</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="4" to-port="0" />
		<edge from-layer="2" from-port="0" to-layer="3" to-port="1" />
		<edge from-layer="3" from-port="2" to-layer="37" to-port="0" />
		<edge from-layer="4" from-port="1" to-layer="5" to-port="0" />
		<edge from-layer="4" from-port="1" to-layer="12" to-port="1" />
		<edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
		<edge from-layer="5" from-port="1" to-layer="18" to-port="0" />
		<edge from-layer="6" from-port="0" to-layer="8" to-port="1" />
		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
		<edge from-layer="8" from-port="3" to-layer="36" to-port="0" />
		<edge from-layer="9" from-port="0" to-layer="36" to-port="1" />
		<edge from-layer="9" from-port="0" to-layer="36" to-port="2" />
		<edge from-layer="10" from-port="0" to-layer="12" to-port="0" />
		<edge from-layer="11" from-port="0" to-layer="12" to-port="2" />
		<edge from-layer="12" from-port="3" to-layer="25" to-port="0" />
		<edge from-layer="13" from-port="0" to-layer="24" to-port="0" />
		<edge from-layer="14" from-port="0" to-layer="21" to-port="0" />
		<edge from-layer="15" from-port="0" to-layer="21" to-port="1" />
		<edge from-layer="16" from-port="0" to-layer="18" to-port="1" />
		<edge from-layer="17" from-port="0" to-layer="18" to-port="2" />
		<edge from-layer="18" from-port="3" to-layer="21" to-port="2" />
		<edge from-layer="19" from-port="0" to-layer="21" to-port="3" />
		<edge from-layer="20" from-port="0" to-layer="21" to-port="4" />
		<edge from-layer="21" from-port="5" to-layer="22" to-port="0" />
		<edge from-layer="22" from-port="1" to-layer="24" to-port="1" />
		<edge from-layer="23" from-port="0" to-layer="24" to-port="2" />
		<edge from-layer="24" from-port="3" to-layer="25" to-port="1" />
		<edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
		<edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
		<edge from-layer="27" from-port="2" to-layer="29" to-port="0" />
		<edge from-layer="28" from-port="0" to-layer="29" to-port="1" />
		<edge from-layer="29" from-port="2" to-layer="31" to-port="0" />
		<edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
		<edge from-layer="31" from-port="2" to-layer="32" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="39" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="49" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="63" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="79" to-port="1" />
		<edge from-layer="32" from-port="1" to-layer="35" to-port="0" />
		<edge from-layer="33" from-port="0" to-layer="35" to-port="1" />
		<edge from-layer="34" from-port="0" to-layer="35" to-port="2" />
		<edge from-layer="35" from-port="3" to-layer="36" to-port="3" />
		<edge from-layer="36" from-port="4" to-layer="37" to-port="1" />
		<edge from-layer="37" from-port="2" to-layer="58" to-port="0" />
		<edge from-layer="37" from-port="2" to-layer="250" to-port="0" />
		<edge from-layer="37" from-port="2" to-layer="314" to-port="0" />
		<edge from-layer="37" from-port="2" to-layer="122" to-port="0" />
		<edge from-layer="37" from-port="2" to-layer="378" to-port="0" />
		<edge from-layer="37" from-port="2" to-layer="186" to-port="0" />
		<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
		<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
		<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
		<edge from-layer="41" from-port="2" to-layer="43" to-port="0" />
		<edge from-layer="42" from-port="0" to-layer="43" to-port="1" />
		<edge from-layer="43" from-port="2" to-layer="45" to-port="0" />
		<edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
		<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
		<edge from-layer="47" from-port="2" to-layer="56" to-port="0" />
		<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
		<edge from-layer="49" from-port="2" to-layer="51" to-port="0" />
		<edge from-layer="50" from-port="0" to-layer="51" to-port="1" />
		<edge from-layer="51" from-port="2" to-layer="53" to-port="0" />
		<edge from-layer="52" from-port="0" to-layer="53" to-port="1" />
		<edge from-layer="53" from-port="2" to-layer="55" to-port="0" />
		<edge from-layer="54" from-port="0" to-layer="55" to-port="1" />
		<edge from-layer="55" from-port="2" to-layer="56" to-port="1" />
		<edge from-layer="56" from-port="2" to-layer="60" to-port="2" />
		<edge from-layer="56" from-port="2" to-layer="57" to-port="0" />
		<edge from-layer="57" from-port="1" to-layer="58" to-port="1" />
		<edge from-layer="58" from-port="2" to-layer="60" to-port="0" />
		<edge from-layer="59" from-port="0" to-layer="60" to-port="1" />
		<edge from-layer="60" from-port="3" to-layer="61" to-port="0" />
		<edge from-layer="61" from-port="1" to-layer="70" to-port="0" />
		<edge from-layer="62" from-port="0" to-layer="63" to-port="1" />
		<edge from-layer="63" from-port="2" to-layer="65" to-port="0" />
		<edge from-layer="64" from-port="0" to-layer="65" to-port="1" />
		<edge from-layer="65" from-port="2" to-layer="67" to-port="0" />
		<edge from-layer="66" from-port="0" to-layer="67" to-port="1" />
		<edge from-layer="67" from-port="2" to-layer="69" to-port="0" />
		<edge from-layer="68" from-port="0" to-layer="69" to-port="1" />
		<edge from-layer="69" from-port="2" to-layer="70" to-port="1" />
		<edge from-layer="70" from-port="2" to-layer="72" to-port="0" />
		<edge from-layer="71" from-port="0" to-layer="72" to-port="1" />
		<edge from-layer="72" from-port="2" to-layer="74" to-port="0" />
		<edge from-layer="73" from-port="0" to-layer="74" to-port="1" />
		<edge from-layer="74" from-port="2" to-layer="76" to-port="0" />
		<edge from-layer="75" from-port="0" to-layer="76" to-port="1" />
		<edge from-layer="76" from-port="2" to-layer="78" to-port="0" />
		<edge from-layer="77" from-port="0" to-layer="78" to-port="1" />
		<edge from-layer="78" from-port="2" to-layer="79" to-port="0" />
		<edge from-layer="79" from-port="2" to-layer="81" to-port="0" />
		<edge from-layer="80" from-port="0" to-layer="81" to-port="1" />
		<edge from-layer="81" from-port="2" to-layer="83" to-port="0" />
		<edge from-layer="82" from-port="0" to-layer="83" to-port="1" />
		<edge from-layer="83" from-port="2" to-layer="85" to-port="0" />
		<edge from-layer="84" from-port="0" to-layer="85" to-port="1" />
		<edge from-layer="85" from-port="2" to-layer="87" to-port="0" />
		<edge from-layer="85" from-port="2" to-layer="95" to-port="1" />
		<edge from-layer="86" from-port="0" to-layer="87" to-port="1" />
		<edge from-layer="87" from-port="2" to-layer="89" to-port="0" />
		<edge from-layer="88" from-port="0" to-layer="89" to-port="1" />
		<edge from-layer="89" from-port="2" to-layer="90" to-port="0" />
		<edge from-layer="90" from-port="1" to-layer="92" 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="94" to-port="0" />
		<edge from-layer="93" from-port="0" to-layer="94" to-port="1" />
		<edge from-layer="94" from-port="2" to-layer="95" to-port="0" />
		<edge from-layer="95" from-port="2" to-layer="97" to-port="0" />
		<edge from-layer="96" from-port="0" to-layer="97" to-port="1" />
		<edge from-layer="97" from-port="2" to-layer="99" to-port="0" />
		<edge from-layer="98" from-port="0" to-layer="99" to-port="1" />
		<edge from-layer="99" from-port="2" to-layer="101" to-port="0" />
		<edge from-layer="100" from-port="0" to-layer="101" to-port="1" />
		<edge from-layer="101" from-port="2" to-layer="103" to-port="0" />
		<edge from-layer="101" from-port="2" to-layer="113" to-port="0" />
		<edge from-layer="101" from-port="2" to-layer="127" to-port="0" />
		<edge from-layer="101" from-port="2" to-layer="143" to-port="1" />
		<edge from-layer="102" from-port="0" to-layer="103" to-port="1" />
		<edge from-layer="103" from-port="2" to-layer="105" to-port="0" />
		<edge from-layer="104" from-port="0" to-layer="105" to-port="1" />
		<edge from-layer="105" from-port="2" to-layer="107" to-port="0" />
		<edge from-layer="106" from-port="0" to-layer="107" to-port="1" />
		<edge from-layer="107" from-port="2" to-layer="109" to-port="0" />
		<edge from-layer="108" from-port="0" to-layer="109" to-port="1" />
		<edge from-layer="109" from-port="2" to-layer="111" to-port="0" />
		<edge from-layer="110" from-port="0" to-layer="111" to-port="1" />
		<edge from-layer="111" from-port="2" to-layer="120" 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="117" to-port="0" />
		<edge from-layer="116" from-port="0" to-layer="117" to-port="1" />
		<edge from-layer="117" from-port="2" to-layer="119" to-port="0" />
		<edge from-layer="118" from-port="0" to-layer="119" to-port="1" />
		<edge from-layer="119" from-port="2" to-layer="120" to-port="1" />
		<edge from-layer="120" from-port="2" to-layer="121" to-port="0" />
		<edge from-layer="120" from-port="2" to-layer="124" to-port="2" />
		<edge from-layer="121" from-port="1" to-layer="122" to-port="1" />
		<edge from-layer="122" from-port="2" to-layer="124" to-port="0" />
		<edge from-layer="123" from-port="0" to-layer="124" to-port="1" />
		<edge from-layer="124" from-port="3" to-layer="125" to-port="0" />
		<edge from-layer="125" from-port="1" to-layer="134" 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="129" to-port="0" />
		<edge from-layer="128" from-port="0" to-layer="129" to-port="1" />
		<edge from-layer="129" from-port="2" to-layer="131" to-port="0" />
		<edge from-layer="130" from-port="0" to-layer="131" to-port="1" />
		<edge from-layer="131" from-port="2" to-layer="133" to-port="0" />
		<edge from-layer="132" from-port="0" to-layer="133" to-port="1" />
		<edge from-layer="133" from-port="2" to-layer="134" to-port="1" />
		<edge from-layer="134" from-port="2" to-layer="136" to-port="0" />
		<edge from-layer="135" from-port="0" to-layer="136" to-port="1" />
		<edge from-layer="136" from-port="2" to-layer="138" to-port="0" />
		<edge from-layer="137" from-port="0" to-layer="138" to-port="1" />
		<edge from-layer="138" from-port="2" to-layer="140" to-port="0" />
		<edge from-layer="139" from-port="0" to-layer="140" to-port="1" />
		<edge from-layer="140" from-port="2" to-layer="142" to-port="0" />
		<edge from-layer="141" from-port="0" to-layer="142" to-port="1" />
		<edge from-layer="142" from-port="2" to-layer="143" to-port="0" />
		<edge from-layer="143" from-port="2" to-layer="145" to-port="0" />
		<edge from-layer="144" from-port="0" to-layer="145" to-port="1" />
		<edge from-layer="145" from-port="2" to-layer="147" to-port="0" />
		<edge from-layer="146" from-port="0" to-layer="147" to-port="1" />
		<edge from-layer="147" from-port="2" to-layer="149" to-port="0" />
		<edge from-layer="148" from-port="0" to-layer="149" to-port="1" />
		<edge from-layer="149" from-port="2" to-layer="151" to-port="0" />
		<edge from-layer="149" from-port="2" to-layer="159" to-port="1" />
		<edge from-layer="150" from-port="0" to-layer="151" to-port="1" />
		<edge from-layer="151" from-port="2" to-layer="153" to-port="0" />
		<edge from-layer="152" from-port="0" 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="156" to-port="0" />
		<edge from-layer="155" from-port="0" to-layer="156" to-port="1" />
		<edge from-layer="156" from-port="2" to-layer="158" to-port="0" />
		<edge from-layer="157" from-port="0" to-layer="158" to-port="1" />
		<edge from-layer="158" from-port="2" to-layer="159" to-port="0" />
		<edge from-layer="159" from-port="2" to-layer="161" to-port="0" />
		<edge from-layer="160" from-port="0" to-layer="161" to-port="1" />
		<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="165" to-port="0" />
		<edge from-layer="164" from-port="0" to-layer="165" to-port="1" />
		<edge from-layer="165" from-port="2" to-layer="177" to-port="0" />
		<edge from-layer="165" from-port="2" to-layer="167" to-port="0" />
		<edge from-layer="165" from-port="2" to-layer="191" to-port="0" />
		<edge from-layer="165" from-port="2" to-layer="207" to-port="1" />
		<edge from-layer="166" from-port="0" to-layer="167" to-port="1" />
		<edge from-layer="167" from-port="2" to-layer="169" to-port="0" />
		<edge from-layer="168" from-port="0" to-layer="169" to-port="1" />
		<edge from-layer="169" from-port="2" to-layer="171" to-port="0" />
		<edge from-layer="170" from-port="0" to-layer="171" to-port="1" />
		<edge from-layer="171" from-port="2" to-layer="173" to-port="0" />
		<edge from-layer="172" from-port="0" to-layer="173" to-port="1" />
		<edge from-layer="173" from-port="2" to-layer="175" to-port="0" />
		<edge from-layer="174" from-port="0" to-layer="175" to-port="1" />
		<edge from-layer="175" from-port="2" to-layer="184" 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="181" to-port="0" />
		<edge from-layer="180" from-port="0" to-layer="181" to-port="1" />
		<edge from-layer="181" from-port="2" to-layer="183" to-port="0" />
		<edge from-layer="182" from-port="0" to-layer="183" to-port="1" />
		<edge from-layer="183" from-port="2" to-layer="184" to-port="1" />
		<edge from-layer="184" from-port="2" to-layer="185" to-port="0" />
		<edge from-layer="184" from-port="2" to-layer="188" to-port="2" />
		<edge from-layer="185" from-port="1" to-layer="186" to-port="1" />
		<edge from-layer="186" from-port="2" to-layer="188" to-port="0" />
		<edge from-layer="187" from-port="0" to-layer="188" to-port="1" />
		<edge from-layer="188" from-port="3" to-layer="189" to-port="0" />
		<edge from-layer="189" from-port="1" to-layer="198" to-port="0" />
		<edge from-layer="190" from-port="0" to-layer="191" to-port="1" />
		<edge from-layer="191" from-port="2" to-layer="193" to-port="0" />
		<edge from-layer="192" from-port="0" to-layer="193" to-port="1" />
		<edge from-layer="193" from-port="2" to-layer="195" to-port="0" />
		<edge from-layer="194" from-port="0" to-layer="195" to-port="1" />
		<edge from-layer="195" from-port="2" to-layer="197" to-port="0" />
		<edge from-layer="196" from-port="0" to-layer="197" to-port="1" />
		<edge from-layer="197" from-port="2" to-layer="198" to-port="1" />
		<edge from-layer="198" from-port="2" to-layer="200" to-port="0" />
		<edge from-layer="199" from-port="0" to-layer="200" to-port="1" />
		<edge from-layer="200" from-port="2" to-layer="202" to-port="0" />
		<edge from-layer="201" from-port="0" to-layer="202" to-port="1" />
		<edge from-layer="202" from-port="2" to-layer="204" to-port="0" />
		<edge from-layer="203" from-port="0" to-layer="204" to-port="1" />
		<edge from-layer="204" from-port="2" to-layer="206" to-port="0" />
		<edge from-layer="205" from-port="0" to-layer="206" to-port="1" />
		<edge from-layer="206" from-port="2" to-layer="207" to-port="0" />
		<edge from-layer="207" from-port="2" to-layer="209" to-port="0" />
		<edge from-layer="208" from-port="0" to-layer="209" to-port="1" />
		<edge from-layer="209" from-port="2" to-layer="211" to-port="0" />
		<edge from-layer="210" from-port="0" to-layer="211" to-port="1" />
		<edge from-layer="211" from-port="2" to-layer="213" to-port="0" />
		<edge from-layer="212" from-port="0" to-layer="213" to-port="1" />
		<edge from-layer="213" from-port="2" to-layer="223" to-port="1" />
		<edge from-layer="213" from-port="2" to-layer="215" to-port="0" />
		<edge from-layer="214" from-port="0" to-layer="215" to-port="1" />
		<edge from-layer="215" from-port="2" to-layer="217" to-port="0" />
		<edge from-layer="216" from-port="0" to-layer="217" to-port="1" />
		<edge from-layer="217" from-port="2" to-layer="218" to-port="0" />
		<edge from-layer="218" from-port="1" to-layer="220" to-port="0" />
		<edge from-layer="219" from-port="0" to-layer="220" to-port="1" />
		<edge from-layer="220" from-port="2" to-layer="222" to-port="0" />
		<edge from-layer="221" from-port="0" to-layer="222" to-port="1" />
		<edge from-layer="222" from-port="2" to-layer="223" to-port="0" />
		<edge from-layer="223" from-port="2" to-layer="225" to-port="0" />
		<edge from-layer="224" from-port="0" to-layer="225" to-port="1" />
		<edge from-layer="225" from-port="2" to-layer="227" to-port="0" />
		<edge from-layer="226" from-port="0" to-layer="227" to-port="1" />
		<edge from-layer="227" from-port="2" to-layer="229" to-port="0" />
		<edge from-layer="228" from-port="0" to-layer="229" to-port="1" />
		<edge from-layer="229" from-port="2" to-layer="231" to-port="0" />
		<edge from-layer="229" from-port="2" to-layer="241" to-port="0" />
		<edge from-layer="229" from-port="2" to-layer="255" to-port="0" />
		<edge from-layer="229" from-port="2" to-layer="271" to-port="1" />
		<edge from-layer="230" from-port="0" to-layer="231" to-port="1" />
		<edge from-layer="231" from-port="2" to-layer="233" to-port="0" />
		<edge from-layer="232" from-port="0" to-layer="233" to-port="1" />
		<edge from-layer="233" from-port="2" to-layer="235" to-port="0" />
		<edge from-layer="234" from-port="0" to-layer="235" to-port="1" />
		<edge from-layer="235" from-port="2" to-layer="237" to-port="0" />
		<edge from-layer="236" from-port="0" to-layer="237" to-port="1" />
		<edge from-layer="237" from-port="2" to-layer="239" to-port="0" />
		<edge from-layer="238" from-port="0" to-layer="239" to-port="1" />
		<edge from-layer="239" from-port="2" to-layer="248" to-port="0" />
		<edge from-layer="240" from-port="0" to-layer="241" to-port="1" />
		<edge from-layer="241" from-port="2" to-layer="243" to-port="0" />
		<edge from-layer="242" from-port="0" to-layer="243" to-port="1" />
		<edge from-layer="243" from-port="2" to-layer="245" to-port="0" />
		<edge from-layer="244" from-port="0" to-layer="245" to-port="1" />
		<edge from-layer="245" from-port="2" to-layer="247" to-port="0" />
		<edge from-layer="246" from-port="0" to-layer="247" to-port="1" />
		<edge from-layer="247" from-port="2" to-layer="248" to-port="1" />
		<edge from-layer="248" from-port="2" to-layer="249" to-port="0" />
		<edge from-layer="248" from-port="2" to-layer="252" to-port="2" />
		<edge from-layer="249" from-port="1" to-layer="250" to-port="1" />
		<edge from-layer="250" from-port="2" to-layer="252" to-port="0" />
		<edge from-layer="251" from-port="0" to-layer="252" to-port="1" />
		<edge from-layer="252" from-port="3" to-layer="253" to-port="0" />
		<edge from-layer="253" from-port="1" to-layer="262" 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="259" to-port="0" />
		<edge from-layer="258" from-port="0" to-layer="259" to-port="1" />
		<edge from-layer="259" from-port="2" to-layer="261" to-port="0" />
		<edge from-layer="260" from-port="0" to-layer="261" to-port="1" />
		<edge from-layer="261" from-port="2" to-layer="262" to-port="1" />
		<edge from-layer="262" from-port="2" to-layer="264" to-port="0" />
		<edge from-layer="263" from-port="0" to-layer="264" to-port="1" />
		<edge from-layer="264" from-port="2" to-layer="266" to-port="0" />
		<edge from-layer="265" from-port="0" to-layer="266" to-port="1" />
		<edge from-layer="266" from-port="2" to-layer="268" to-port="0" />
		<edge from-layer="267" from-port="0" to-layer="268" to-port="1" />
		<edge from-layer="268" from-port="2" to-layer="270" to-port="0" />
		<edge from-layer="269" from-port="0" to-layer="270" to-port="1" />
		<edge from-layer="270" from-port="2" to-layer="271" to-port="0" />
		<edge from-layer="271" from-port="2" to-layer="273" to-port="0" />
		<edge from-layer="272" from-port="0" to-layer="273" to-port="1" />
		<edge from-layer="273" from-port="2" to-layer="275" to-port="0" />
		<edge from-layer="274" from-port="0" to-layer="275" to-port="1" />
		<edge from-layer="275" from-port="2" to-layer="277" to-port="0" />
		<edge from-layer="276" from-port="0" to-layer="277" to-port="1" />
		<edge from-layer="277" from-port="2" to-layer="279" to-port="0" />
		<edge from-layer="277" from-port="2" to-layer="287" to-port="1" />
		<edge from-layer="278" from-port="0" to-layer="279" to-port="1" />
		<edge from-layer="279" from-port="2" to-layer="281" to-port="0" />
		<edge from-layer="280" from-port="0" to-layer="281" to-port="1" />
		<edge from-layer="281" from-port="2" to-layer="282" to-port="0" />
		<edge from-layer="282" from-port="1" to-layer="284" to-port="0" />
		<edge from-layer="283" from-port="0" to-layer="284" to-port="1" />
		<edge from-layer="284" from-port="2" to-layer="286" to-port="0" />
		<edge from-layer="285" from-port="0" to-layer="286" to-port="1" />
		<edge from-layer="286" from-port="2" to-layer="287" to-port="0" />
		<edge from-layer="287" from-port="2" to-layer="289" to-port="0" />
		<edge from-layer="288" from-port="0" to-layer="289" to-port="1" />
		<edge from-layer="289" from-port="2" to-layer="291" to-port="0" />
		<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
		<edge from-layer="291" from-port="2" to-layer="293" to-port="0" />
		<edge from-layer="292" from-port="0" to-layer="293" to-port="1" />
		<edge from-layer="293" from-port="2" to-layer="295" to-port="0" />
		<edge from-layer="293" from-port="2" to-layer="305" to-port="0" />
		<edge from-layer="293" from-port="2" to-layer="319" to-port="0" />
		<edge from-layer="293" from-port="2" to-layer="335" to-port="1" />
		<edge from-layer="294" from-port="0" to-layer="295" to-port="1" />
		<edge from-layer="295" from-port="2" to-layer="297" to-port="0" />
		<edge from-layer="296" from-port="0" to-layer="297" to-port="1" />
		<edge from-layer="297" from-port="2" to-layer="299" to-port="0" />
		<edge from-layer="298" from-port="0" to-layer="299" to-port="1" />
		<edge from-layer="299" from-port="2" to-layer="301" to-port="0" />
		<edge from-layer="300" from-port="0" to-layer="301" to-port="1" />
		<edge from-layer="301" from-port="2" to-layer="303" to-port="0" />
		<edge from-layer="302" from-port="0" to-layer="303" to-port="1" />
		<edge from-layer="303" from-port="2" to-layer="312" to-port="0" />
		<edge from-layer="304" from-port="0" to-layer="305" to-port="1" />
		<edge from-layer="305" from-port="2" to-layer="307" to-port="0" />
		<edge from-layer="306" from-port="0" to-layer="307" to-port="1" />
		<edge from-layer="307" from-port="2" to-layer="309" to-port="0" />
		<edge from-layer="308" from-port="0" to-layer="309" to-port="1" />
		<edge from-layer="309" from-port="2" to-layer="311" to-port="0" />
		<edge from-layer="310" from-port="0" to-layer="311" to-port="1" />
		<edge from-layer="311" from-port="2" to-layer="312" to-port="1" />
		<edge from-layer="312" from-port="2" to-layer="313" to-port="0" />
		<edge from-layer="312" from-port="2" to-layer="316" to-port="2" />
		<edge from-layer="313" from-port="1" to-layer="314" to-port="1" />
		<edge from-layer="314" from-port="2" to-layer="316" to-port="0" />
		<edge from-layer="315" from-port="0" to-layer="316" to-port="1" />
		<edge from-layer="316" from-port="3" to-layer="317" to-port="0" />
		<edge from-layer="317" from-port="1" to-layer="326" to-port="0" />
		<edge from-layer="318" from-port="0" to-layer="319" to-port="1" />
		<edge from-layer="319" from-port="2" to-layer="321" to-port="0" />
		<edge from-layer="320" from-port="0" to-layer="321" to-port="1" />
		<edge from-layer="321" from-port="2" to-layer="323" to-port="0" />
		<edge from-layer="322" from-port="0" to-layer="323" to-port="1" />
		<edge from-layer="323" from-port="2" to-layer="325" to-port="0" />
		<edge from-layer="324" from-port="0" to-layer="325" to-port="1" />
		<edge from-layer="325" from-port="2" to-layer="326" to-port="1" />
		<edge from-layer="326" from-port="2" to-layer="328" to-port="0" />
		<edge from-layer="327" from-port="0" to-layer="328" to-port="1" />
		<edge from-layer="328" from-port="2" to-layer="330" to-port="0" />
		<edge from-layer="329" from-port="0" to-layer="330" to-port="1" />
		<edge from-layer="330" from-port="2" to-layer="332" to-port="0" />
		<edge from-layer="331" from-port="0" to-layer="332" to-port="1" />
		<edge from-layer="332" from-port="2" to-layer="334" to-port="0" />
		<edge from-layer="333" from-port="0" to-layer="334" to-port="1" />
		<edge from-layer="334" from-port="2" to-layer="335" to-port="0" />
		<edge from-layer="335" from-port="2" to-layer="337" to-port="0" />
		<edge from-layer="336" from-port="0" to-layer="337" to-port="1" />
		<edge from-layer="337" from-port="2" to-layer="339" to-port="0" />
		<edge from-layer="338" from-port="0" to-layer="339" to-port="1" />
		<edge from-layer="339" from-port="2" to-layer="341" to-port="0" />
		<edge from-layer="340" from-port="0" to-layer="341" to-port="1" />
		<edge from-layer="341" from-port="2" to-layer="343" to-port="0" />
		<edge from-layer="341" from-port="2" to-layer="351" to-port="1" />
		<edge from-layer="342" from-port="0" to-layer="343" to-port="1" />
		<edge from-layer="343" from-port="2" to-layer="345" to-port="0" />
		<edge from-layer="344" from-port="0" to-layer="345" to-port="1" />
		<edge from-layer="345" from-port="2" to-layer="346" to-port="0" />
		<edge from-layer="346" from-port="1" to-layer="348" to-port="0" />
		<edge from-layer="347" from-port="0" to-layer="348" to-port="1" />
		<edge from-layer="348" from-port="2" to-layer="350" to-port="0" />
		<edge from-layer="349" from-port="0" to-layer="350" to-port="1" />
		<edge from-layer="350" from-port="2" to-layer="351" to-port="0" />
		<edge from-layer="351" from-port="2" to-layer="353" to-port="0" />
		<edge from-layer="352" from-port="0" to-layer="353" to-port="1" />
		<edge from-layer="353" from-port="2" to-layer="355" to-port="0" />
		<edge from-layer="354" from-port="0" to-layer="355" to-port="1" />
		<edge from-layer="355" from-port="2" to-layer="357" to-port="0" />
		<edge from-layer="356" from-port="0" to-layer="357" to-port="1" />
		<edge from-layer="357" from-port="2" to-layer="359" to-port="0" />
		<edge from-layer="357" from-port="2" to-layer="369" to-port="0" />
		<edge from-layer="357" from-port="2" to-layer="383" to-port="0" />
		<edge from-layer="357" from-port="2" to-layer="399" to-port="1" />
		<edge from-layer="358" from-port="0" to-layer="359" to-port="1" />
		<edge from-layer="359" from-port="2" to-layer="361" to-port="0" />
		<edge from-layer="360" from-port="0" to-layer="361" to-port="1" />
		<edge from-layer="361" from-port="2" to-layer="363" to-port="0" />
		<edge from-layer="362" from-port="0" to-layer="363" to-port="1" />
		<edge from-layer="363" from-port="2" to-layer="365" to-port="0" />
		<edge from-layer="364" from-port="0" to-layer="365" to-port="1" />
		<edge from-layer="365" from-port="2" to-layer="367" to-port="0" />
		<edge from-layer="366" from-port="0" to-layer="367" to-port="1" />
		<edge from-layer="367" from-port="2" to-layer="376" to-port="0" />
		<edge from-layer="368" from-port="0" to-layer="369" to-port="1" />
		<edge from-layer="369" from-port="2" to-layer="371" to-port="0" />
		<edge from-layer="370" from-port="0" to-layer="371" to-port="1" />
		<edge from-layer="371" from-port="2" to-layer="373" to-port="0" />
		<edge from-layer="372" from-port="0" to-layer="373" to-port="1" />
		<edge from-layer="373" from-port="2" to-layer="375" to-port="0" />
		<edge from-layer="374" from-port="0" to-layer="375" to-port="1" />
		<edge from-layer="375" from-port="2" to-layer="376" to-port="1" />
		<edge from-layer="376" from-port="2" to-layer="377" to-port="0" />
		<edge from-layer="376" from-port="2" to-layer="380" to-port="2" />
		<edge from-layer="377" from-port="1" to-layer="378" to-port="1" />
		<edge from-layer="378" from-port="2" to-layer="380" to-port="0" />
		<edge from-layer="379" from-port="0" to-layer="380" to-port="1" />
		<edge from-layer="380" from-port="3" to-layer="381" to-port="0" />
		<edge from-layer="381" from-port="1" to-layer="390" to-port="0" />
		<edge from-layer="382" from-port="0" to-layer="383" to-port="1" />
		<edge from-layer="383" from-port="2" to-layer="385" to-port="0" />
		<edge from-layer="384" from-port="0" to-layer="385" to-port="1" />
		<edge from-layer="385" from-port="2" to-layer="387" to-port="0" />
		<edge from-layer="386" from-port="0" to-layer="387" to-port="1" />
		<edge from-layer="387" from-port="2" to-layer="389" to-port="0" />
		<edge from-layer="388" from-port="0" to-layer="389" to-port="1" />
		<edge from-layer="389" from-port="2" to-layer="390" to-port="1" />
		<edge from-layer="390" from-port="2" to-layer="392" to-port="0" />
		<edge from-layer="391" from-port="0" to-layer="392" to-port="1" />
		<edge from-layer="392" from-port="2" to-layer="394" to-port="0" />
		<edge from-layer="393" from-port="0" to-layer="394" to-port="1" />
		<edge from-layer="394" from-port="2" to-layer="396" to-port="0" />
		<edge from-layer="395" from-port="0" to-layer="396" to-port="1" />
		<edge from-layer="396" from-port="2" to-layer="398" to-port="0" />
		<edge from-layer="397" from-port="0" to-layer="398" to-port="1" />
		<edge from-layer="398" from-port="2" to-layer="399" to-port="0" />
		<edge from-layer="399" from-port="2" to-layer="401" to-port="0" />
		<edge from-layer="400" from-port="0" to-layer="401" to-port="1" />
		<edge from-layer="401" from-port="2" to-layer="403" to-port="0" />
		<edge from-layer="402" from-port="0" to-layer="403" to-port="1" />
		<edge from-layer="403" from-port="2" to-layer="405" to-port="0" />
		<edge from-layer="404" from-port="0" to-layer="405" to-port="1" />
		<edge from-layer="405" from-port="2" to-layer="407" to-port="0" />
		<edge from-layer="405" from-port="2" to-layer="415" to-port="1" />
		<edge from-layer="406" from-port="0" to-layer="407" to-port="1" />
		<edge from-layer="407" from-port="2" to-layer="409" to-port="0" />
		<edge from-layer="408" from-port="0" to-layer="409" to-port="1" />
		<edge from-layer="409" from-port="2" to-layer="410" to-port="0" />
		<edge from-layer="410" from-port="1" to-layer="412" to-port="0" />
		<edge from-layer="411" from-port="0" to-layer="412" to-port="1" />
		<edge from-layer="412" from-port="2" to-layer="414" to-port="0" />
		<edge from-layer="413" from-port="0" to-layer="414" to-port="1" />
		<edge from-layer="414" from-port="2" to-layer="415" to-port="0" />
		<edge from-layer="415" from-port="2" to-layer="417" to-port="0" />
		<edge from-layer="416" from-port="0" to-layer="417" to-port="1" />
		<edge from-layer="417" from-port="2" to-layer="419" to-port="0" />
		<edge from-layer="418" from-port="0" to-layer="419" to-port="1" />
		<edge from-layer="419" from-port="2" to-layer="421" to-port="0" />
		<edge from-layer="420" from-port="0" to-layer="421" to-port="1" />
		<edge from-layer="421" from-port="2" to-layer="422" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2024.4.1-16618-643f23d1318-releases/2024/4" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<optimum>
			<optimum_intel_version value="1.20.0.dev0+b31524c" />
			<optimum_version value="1.23.0" />
			<pytorch_version value="2.5.0.dev20240807+cu121" />
			<transformers_version value="4.43.4" />
		</optimum>
	</rt_info>
</net>