openvino/openvino_model.xml

<?xml version="1.0"?>
<net name="Model0" version="11">
	<layers>
		<layer id="2" 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="1" 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="0" name="token_type_ids" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="token_type_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="self.embeddings.word_embeddings.weight" type="Const" version="opset1">
			<data element_type="f32" shape="30522, 128" offset="0" size="15627264" />
			<output>
				<port id="0" precision="FP32" names="self.embeddings.word_embeddings.weight">
					<dim>30522</dim>
					<dim>128</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="__module.embeddings.word_embeddings/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="15627264" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="6" name="__module.embeddings.word_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>30522</dim>
					<dim>128</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="79,inputs_embeds">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="self.embeddings.token_type_embeddings.weight" type="Const" version="opset1">
			<data element_type="f32" shape="2, 128" offset="15627268" size="1024" />
			<output>
				<port id="0" precision="FP32" names="self.embeddings.token_type_embeddings.weight">
					<dim>2</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="__module.embeddings.token_type_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="9" name="__module.embeddings.token_type_embeddings/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="15627264" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="10" name="__module.embeddings.token_type_embeddings/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>2</dim>
					<dim>128</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="81,token_type_embeddings.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="11" 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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="82_1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="self.embeddings.position_embeddings.weight" type="Const" version="opset1">
			<data element_type="f32" shape="512, 128" offset="15628292" size="262144" />
			<output>
				<port id="0" precision="FP32" names="self.embeddings.position_embeddings.weight">
					<dim>512</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="__module.embeddings/aten::slice/Slice" type="Const" version="opset1">
			<data element_type="i64" shape="1, 512" offset="15890436" size="4096" />
			<output>
				<port id="0" precision="I64" names="76">
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="__module.embeddings/aten::slice/Reshape" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="ShapeOf_4117" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="Constant_4238" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="15894540" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="Constant_4119" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="18" name="Gather_4120" 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="10,72,74,75,8">
					<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="15894540" 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="15894540" 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="77">
					<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="15627264" 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>128</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="84,position_embeddings.1">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>128</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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="82,embeddings.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</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="15894548" 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>128</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>128</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="Constant_4060" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="15894552" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="Constant_4061" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="15895064" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="89,input.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="self.encoder.layer.0.attention.self.query.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="15895576" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.0.attention.self.query.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="__module.encoder.layer.0.attention.self.query/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="Constant_4062" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="15961112" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="__module.encoder.layer.0.attention.self.query/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="120,x.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961624" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="__module.encoder.layer.0.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="124,x.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="Constant_238" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961656" size="32" />
			<output>
				<port id="0" precision="I64" names="125">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="__module.encoder.layer.0.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="126">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="self.encoder.layer.0.attention.self.key.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="15961688" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.0.attention.self.key.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="__module.encoder.layer.0.attention.self.key/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="Constant_4063" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16027224" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="__module.encoder.layer.0.attention.self.key/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="129,x.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961624" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="__module.encoder.layer.0.attention.self/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>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="133,x.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="Constant_263" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961656" size="32" />
			<output>
				<port id="0" precision="I64" names="134">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="__module.encoder.layer.0.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="135">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="self.encoder.layer.0.attention.self.value.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="16027736" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.0.attention.self.value.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="__module.encoder.layer.0.attention.self.value/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="Constant_4064" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16093272" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="__module.encoder.layer.0.attention.self.value/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="138,x.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961624" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="__module.encoder.layer.0.attention.self/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>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="142,x.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="Constant_288" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961656" size="32" />
			<output>
				<port id="0" precision="I64" names="143">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="__module.encoder.layer.0.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="144">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="Constant_4066" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="16093784" 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="57" name="25" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="15894540" size="8" />
			<output>
				<port id="0" precision="I64" names="25" />
			</output>
		</layer>
		<layer id="58" name="aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="26">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="27" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="16093788" size="8" />
			<output>
				<port id="0" precision="I64" names="27" />
			</output>
		</layer>
		<layer id="60" name="aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="28,33">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="ShapeOf_4125" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="Constant_4241" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="Constant_4127" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="64" name="Gather_4128" 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="13,15">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="Constant_3694" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="15894540" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Constant_4244" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="15894540" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="Constant_4135" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="68" name="Gather_4136" 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="17,19">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="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="35">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="70" name="aten::expand/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="37">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="aten::to/Convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="42">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="Constant_4065" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1, 1" offset="16093784" 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="73" name="aten::rsub/Multiply" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</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">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="aten::rsub/Subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</dim>
					<dim>1</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="45,inverted_mask">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="aten::to/Convert_1" type="Convert" version="opset1">
			<data destination_type="boolean" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="BOOL" names="50">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="aten::masked_fill/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="16093796" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="77" name="aten::masked_fill/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32" />
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="52">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="__module.encoder.layer.0.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="FP32" names="145,attn_output.1">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.encoder.layer.0.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="16093800" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="__module.encoder.layer.0.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>2</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="146,attn_output.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="__module.encoder.layer.0.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="82" name="Constant_3859" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="16093816" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="Constant_3860" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="84" name="Gather_3861" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Reshape_1_3" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="16093832" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="__module.encoder.layer.0.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="147">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="__module.encoder.layer.0.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="148">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="self.encoder.layer.0.attention.output.dense.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="16093840" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.0.attention.output.dense.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.encoder.layer.0.attention.output.dense/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="Constant_4067" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16159376" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="__module.encoder.layer.0.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="154,input.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="__module.encoder.layer.0.attention.output/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="156">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="__module.encoder.layer.0.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="15894548" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="__module.encoder.layer.0.attention.output.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>128</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>128</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="Constant_4068" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16159888" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="__module.encoder.layer.0.attention.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="Constant_4069" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16160400" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="__module.encoder.layer.0.attention.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="160,input_tensor.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="self.encoder.layer.0.intermediate.dense.weight" type="Const" version="opset1">
			<data element_type="f32" shape="512, 128" offset="16160912" size="262144" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.0.intermediate.dense.weight">
					<dim>512</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="__module.encoder.layer.0.intermediate.dense/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="Constant_4070" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="16423056" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="__module.encoder.layer.0.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="165">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="__module.encoder.layer.0.intermediate.intermediate_act_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="166">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="self.encoder.layer.0.output.dense.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 512" offset="16425104" size="262144" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.0.output.dense.weight">
					<dim>128</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="__module.encoder.layer.0.output.dense/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="Constant_4071" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16687248" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="__module.encoder.layer.0.output.dense/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="172,input.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="__module.encoder.layer.0.output/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="174">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="__module.encoder.layer.0.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="15894548" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="__module.encoder.layer.0.output.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>128</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>128</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="Constant_4072" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16687760" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="__module.encoder.layer.0.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="Constant_4073" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16688272" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="__module.encoder.layer.0.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="178,hidden_states.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="self.encoder.layer.1.attention.self.query.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="16688784" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.1.attention.self.query.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="__module.encoder.layer.1.attention.self.query/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="Constant_4074" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16754320" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="__module.encoder.layer.1.attention.self.query/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="191,x.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961624" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="__module.encoder.layer.1.attention.self/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="195,x.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="Constant_446" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961656" size="32" />
			<output>
				<port id="0" precision="I64" names="196">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="__module.encoder.layer.1.attention.self/aten::permute/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="197">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="self.encoder.layer.1.attention.self.key.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="16754832" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.1.attention.self.key.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="124" name="__module.encoder.layer.1.attention.self.key/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="Constant_4075" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16820368" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="__module.encoder.layer.1.attention.self.key/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="200,x.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat_1" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961624" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="__module.encoder.layer.1.attention.self/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>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="204,x.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="Constant_469" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961656" size="32" />
			<output>
				<port id="0" precision="I64" names="205">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="__module.encoder.layer.1.attention.self/aten::permute/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="206">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="self.encoder.layer.1.attention.self.value.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="16820880" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.1.attention.self.value.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="__module.encoder.layer.1.attention.self.value/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="Constant_4076" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16886416" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="__module.encoder.layer.1.attention.self.value/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="209,x.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="135" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat_2" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961624" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="__module.encoder.layer.1.attention.self/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>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="213,x">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="Constant_492" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="15961656" size="32" />
			<output>
				<port id="0" precision="I64" names="214">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="__module.encoder.layer.1.attention.self/aten::permute/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="215">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="__module.encoder.layer.1.attention.self/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="FP32" names="216,attn_output.5">
					<dim>-1</dim>
					<dim>2</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="__module.encoder.layer.1.attention.self/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="16093800" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="__module.encoder.layer.1.attention.self/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>2</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="217,attn_output">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="__module.encoder.layer.1.attention.self/aten::size/ShapeOf_6" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="Constant_3879" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="16093816" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="Constant_3880" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="15894532" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="145" name="Gather_3881" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="__module.encoder.layer.1.attention.self/prim::ListConstruct/Concat_3" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="218">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="__module.encoder.layer.1.attention.self/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="219">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="self.encoder.layer.1.attention.output.dense.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 128" offset="16886928" size="65536" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.1.attention.output.dense.weight">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="__module.encoder.layer.1.attention.output.dense/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="Constant_4077" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16952464" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="__module.encoder.layer.1.attention.output.dense/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="225,input.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="__module.encoder.layer.1.attention.output/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="227">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="__module.encoder.layer.1.attention.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="15894548" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="__module.encoder.layer.1.attention.output.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>128</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>128</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="Constant_4078" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16952976" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="__module.encoder.layer.1.attention.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="Constant_4079" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="16953488" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="__module.encoder.layer.1.attention.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="231,input_tensor">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="159" name="self.encoder.layer.1.intermediate.dense.weight" type="Const" version="opset1">
			<data element_type="f32" shape="512, 128" offset="16954000" size="262144" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.1.intermediate.dense.weight">
					<dim>512</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="__module.encoder.layer.1.intermediate.dense/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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>512</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="Constant_4080" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 512" offset="17216144" size="2048" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="__module.encoder.layer.1.intermediate.dense/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="236">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="__module.encoder.layer.1.intermediate.intermediate_act_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="237">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="self.encoder.layer.1.output.dense.weight" type="Const" version="opset1">
			<data element_type="f32" shape="128, 512" offset="17218192" size="262144" />
			<output>
				<port id="0" precision="FP32" names="self.encoder.layer.1.output.dense.weight">
					<dim>128</dim>
					<dim>512</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="__module.encoder.layer.1.output.dense/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>512</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>128</dim>
					<dim>512</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="Constant_4081" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="17480336" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="__module.encoder.layer.1.output.dense/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="243,input">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="168" name="__module.encoder.layer.1.output/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="245">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="__module.encoder.layer.1.output.LayerNorm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="15894548" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="__module.encoder.layer.1.output.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>128</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>128</dim>
				</port>
			</output>
		</layer>
		<layer id="171" name="Constant_4082" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="17480848" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="__module.encoder.layer.1.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="Constant_4083" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 128" offset="17481360" size="512" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="__module.encoder.layer.1.output.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>128</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="last_hidden_state">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="Result_1289" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>128</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="8" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="58" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="61" to-port="0" />
		<edge from-layer="2" from-port="0" to-layer="4" to-port="0" />
		<edge from-layer="2" from-port="0" to-layer="15" to-port="0" />
		<edge from-layer="3" from-port="0" to-layer="6" to-port="0" />
		<edge from-layer="4" from-port="1" to-layer="6" to-port="1" />
		<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
		<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
		<edge from-layer="7" from-port="0" to-layer="10" to-port="0" />
		<edge from-layer="8" from-port="1" to-layer="10" to-port="1" />
		<edge from-layer="9" from-port="0" to-layer="10" to-port="2" />
		<edge from-layer="10" from-port="3" to-layer="11" to-port="1" />
		<edge from-layer="11" from-port="2" to-layer="25" to-port="0" />
		<edge from-layer="12" from-port="0" to-layer="24" to-port="0" />
		<edge from-layer="13" from-port="0" to-layer="21" to-port="0" />
		<edge from-layer="14" from-port="0" to-layer="21" to-port="1" />
		<edge from-layer="15" from-port="1" to-layer="18" to-port="0" />
		<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="18" from-port="3" to-layer="69" 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="41" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="92" to-port="1" />
		<edge from-layer="31" from-port="2" to-layer="49" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="33" to-port="0" />
		<edge from-layer="31" from-port="2" to-layer="81" to-port="0" />
		<edge from-layer="32" from-port="0" to-layer="33" to-port="1" />
		<edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
		<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
		<edge from-layer="35" from-port="2" to-layer="37" to-port="0" />
		<edge from-layer="36" from-port="0" to-layer="37" to-port="1" />
		<edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
		<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
		<edge from-layer="39" from-port="2" to-layer="78" 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="78" to-port="1" />
		<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="78" to-port="2" />
		<edge from-layer="56" from-port="0" to-layer="74" to-port="0" />
		<edge from-layer="57" from-port="0" to-layer="58" to-port="1" />
		<edge from-layer="58" from-port="2" to-layer="60" to-port="0" />
		<edge from-layer="59" from-port="0" to-layer="60" to-port="1" />
		<edge from-layer="60" from-port="2" to-layer="70" to-port="0" />
		<edge from-layer="61" from-port="1" to-layer="64" to-port="0" />
		<edge from-layer="61" from-port="1" to-layer="68" to-port="0" />
		<edge from-layer="62" from-port="0" to-layer="64" to-port="1" />
		<edge from-layer="63" from-port="0" to-layer="64" to-port="2" />
		<edge from-layer="64" from-port="3" to-layer="69" to-port="0" />
		<edge from-layer="65" from-port="0" to-layer="69" to-port="1" />
		<edge from-layer="66" from-port="0" to-layer="68" to-port="1" />
		<edge from-layer="67" from-port="0" to-layer="68" to-port="2" />
		<edge from-layer="68" from-port="3" to-layer="69" to-port="3" />
		<edge from-layer="69" from-port="4" to-layer="70" to-port="1" />
		<edge from-layer="70" from-port="2" to-layer="71" to-port="0" />
		<edge from-layer="71" from-port="1" to-layer="73" to-port="0" />
		<edge from-layer="72" from-port="0" to-layer="73" to-port="1" />
		<edge from-layer="73" from-port="2" to-layer="74" to-port="1" />
		<edge from-layer="74" from-port="2" to-layer="77" to-port="2" />
		<edge from-layer="74" from-port="2" to-layer="75" to-port="0" />
		<edge from-layer="75" from-port="1" to-layer="77" to-port="0" />
		<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
		<edge from-layer="77" from-port="3" to-layer="78" to-port="3" />
		<edge from-layer="77" from-port="3" to-layer="139" to-port="3" />
		<edge from-layer="78" from-port="4" to-layer="80" to-port="0" />
		<edge from-layer="79" from-port="0" to-layer="80" to-port="1" />
		<edge from-layer="80" from-port="2" to-layer="87" to-port="0" />
		<edge from-layer="81" from-port="1" to-layer="84" to-port="0" />
		<edge from-layer="82" from-port="0" to-layer="84" to-port="1" />
		<edge from-layer="83" from-port="0" to-layer="84" to-port="2" />
		<edge from-layer="84" from-port="3" to-layer="86" to-port="0" />
		<edge from-layer="85" from-port="0" to-layer="86" to-port="1" />
		<edge from-layer="85" from-port="0" to-layer="146" to-port="1" />
		<edge from-layer="86" from-port="2" to-layer="87" to-port="1" />
		<edge from-layer="87" from-port="2" to-layer="89" to-port="0" />
		<edge from-layer="88" from-port="0" to-layer="89" to-port="1" />
		<edge from-layer="89" from-port="2" to-layer="91" to-port="0" />
		<edge from-layer="90" from-port="0" to-layer="91" to-port="1" />
		<edge from-layer="91" from-port="2" to-layer="92" to-port="0" />
		<edge from-layer="92" from-port="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="96" to-port="0" />
		<edge from-layer="95" from-port="0" to-layer="96" to-port="1" />
		<edge from-layer="96" from-port="2" to-layer="98" to-port="0" />
		<edge from-layer="97" from-port="0" to-layer="98" to-port="1" />
		<edge from-layer="98" from-port="2" to-layer="100" to-port="0" />
		<edge from-layer="98" from-port="2" to-layer="108" to-port="1" />
		<edge from-layer="99" from-port="0" to-layer="100" to-port="1" />
		<edge from-layer="100" from-port="2" to-layer="102" to-port="0" />
		<edge from-layer="101" from-port="0" to-layer="102" to-port="1" />
		<edge from-layer="102" from-port="2" to-layer="103" to-port="0" />
		<edge from-layer="103" from-port="1" to-layer="105" to-port="0" />
		<edge from-layer="104" from-port="0" to-layer="105" to-port="1" />
		<edge from-layer="105" from-port="2" to-layer="107" to-port="0" />
		<edge from-layer="106" from-port="0" to-layer="107" to-port="1" />
		<edge from-layer="107" from-port="2" to-layer="108" to-port="0" />
		<edge from-layer="108" from-port="2" to-layer="110" to-port="0" />
		<edge from-layer="109" from-port="0" to-layer="110" to-port="1" />
		<edge from-layer="110" from-port="2" to-layer="112" to-port="0" />
		<edge from-layer="111" from-port="0" to-layer="112" to-port="1" />
		<edge from-layer="112" from-port="2" to-layer="114" to-port="0" />
		<edge from-layer="113" from-port="0" to-layer="114" to-port="1" />
		<edge from-layer="114" from-port="2" to-layer="124" to-port="0" />
		<edge from-layer="114" from-port="2" to-layer="132" to-port="0" />
		<edge from-layer="114" from-port="2" to-layer="152" to-port="1" />
		<edge from-layer="114" from-port="2" to-layer="142" to-port="0" />
		<edge from-layer="114" from-port="2" to-layer="116" to-port="0" />
		<edge from-layer="115" from-port="0" to-layer="116" to-port="1" />
		<edge from-layer="116" from-port="2" to-layer="118" to-port="0" />
		<edge from-layer="117" from-port="0" to-layer="118" to-port="1" />
		<edge from-layer="118" from-port="2" to-layer="120" to-port="0" />
		<edge from-layer="119" from-port="0" to-layer="120" to-port="1" />
		<edge from-layer="120" from-port="2" to-layer="122" to-port="0" />
		<edge from-layer="121" from-port="0" to-layer="122" to-port="1" />
		<edge from-layer="122" from-port="2" to-layer="139" to-port="0" />
		<edge from-layer="123" from-port="0" to-layer="124" to-port="1" />
		<edge from-layer="124" from-port="2" to-layer="126" to-port="0" />
		<edge from-layer="125" from-port="0" to-layer="126" to-port="1" />
		<edge from-layer="126" from-port="2" to-layer="128" to-port="0" />
		<edge from-layer="127" from-port="0" to-layer="128" to-port="1" />
		<edge from-layer="128" from-port="2" to-layer="130" to-port="0" />
		<edge from-layer="129" from-port="0" to-layer="130" to-port="1" />
		<edge from-layer="130" from-port="2" to-layer="139" to-port="1" />
		<edge from-layer="131" from-port="0" to-layer="132" to-port="1" />
		<edge from-layer="132" from-port="2" to-layer="134" to-port="0" />
		<edge from-layer="133" from-port="0" to-layer="134" to-port="1" />
		<edge from-layer="134" from-port="2" to-layer="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="139" to-port="2" />
		<edge from-layer="139" from-port="4" to-layer="141" to-port="0" />
		<edge from-layer="140" from-port="0" to-layer="141" to-port="1" />
		<edge from-layer="141" from-port="2" to-layer="147" to-port="0" />
		<edge from-layer="142" from-port="1" to-layer="145" to-port="0" />
		<edge from-layer="143" from-port="0" to-layer="145" to-port="1" />
		<edge from-layer="144" from-port="0" to-layer="145" to-port="2" />
		<edge from-layer="145" from-port="3" to-layer="146" to-port="0" />
		<edge from-layer="146" from-port="2" to-layer="147" to-port="1" />
		<edge from-layer="147" from-port="2" to-layer="149" to-port="0" />
		<edge from-layer="148" from-port="0" to-layer="149" to-port="1" />
		<edge from-layer="149" from-port="2" to-layer="151" to-port="0" />
		<edge from-layer="150" from-port="0" to-layer="151" to-port="1" />
		<edge from-layer="151" from-port="2" to-layer="152" to-port="0" />
		<edge from-layer="152" from-port="2" to-layer="154" to-port="0" />
		<edge from-layer="153" from-port="0" to-layer="154" to-port="1" />
		<edge from-layer="154" from-port="2" 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="160" to-port="0" />
		<edge from-layer="158" from-port="2" to-layer="168" to-port="1" />
		<edge from-layer="159" from-port="0" to-layer="160" to-port="1" />
		<edge from-layer="160" from-port="2" to-layer="162" to-port="0" />
		<edge from-layer="161" from-port="0" to-layer="162" to-port="1" />
		<edge from-layer="162" from-port="2" to-layer="163" to-port="0" />
		<edge from-layer="163" from-port="1" 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="167" to-port="0" />
		<edge from-layer="166" from-port="0" to-layer="167" to-port="1" />
		<edge from-layer="167" from-port="2" to-layer="168" to-port="0" />
		<edge from-layer="168" from-port="2" to-layer="170" to-port="0" />
		<edge from-layer="169" from-port="0" to-layer="170" to-port="1" />
		<edge from-layer="170" from-port="2" to-layer="172" to-port="0" />
		<edge from-layer="171" from-port="0" to-layer="172" to-port="1" />
		<edge from-layer="172" from-port="2" to-layer="174" to-port="0" />
		<edge from-layer="173" from-port="0" to-layer="174" to-port="1" />
		<edge from-layer="174" from-port="2" to-layer="175" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2024.3.0-16041-1e3b88e4e3f-releases/2024/3" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<optimum>
			<optimum_intel_version value="1.19.0" />
			<optimum_version value="1.22.0" />
			<pytorch_version value="2.5.0.dev20240807+cu121" />
			<transformers_version value="4.43.4" />
		</optimum>
	</rt_info>
</net>