openvino_decoder_model.xml

<?xml version="1.0"?>
<net name="Model3" version="11">
	<layers>
		<layer id="1" name="decoder_input_ids" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="input_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="0" name="Parameter_26207" type="Parameter" version="opset1">
			<data shape="?,?,?" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="encoder_hidden_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="self.model.model.decoder.embed_tokens.weight" type="Const" version="opset1">
			<data element_type="i8" shape="51866, 1280" offset="0" size="66388480" />
			<output>
				<port id="0" precision="I8">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="Convert_41249" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="self.model.model.decoder.embed_tokens.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="51866, 1" offset="66388480" size="103732" />
			<output>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="Constant_31708" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="66492212" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="__module.model.model.decoder/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="46">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="__module.model.model.decoder.embed_tokens/aten::embedding/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66492228" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="11" name="__module.model.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>51866</dim>
					<dim>1280</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="48,inputs_embeds">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="self.model.model.decoder.embed_positions.weight" type="Const" version="opset1">
			<data element_type="i8" shape="448, 1280" offset="66492232" size="573440" />
			<output>
				<port id="0" precision="I8">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="Convert_41396" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="self.model.model.decoder.embed_positions.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="448, 1" offset="67065672" size="896" />
			<output>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="self.model.model.decoder.embed_positions.weight/fq_weights_0" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="self.model.model.decoder.embed_positions.weight/fq_weights_0/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="23" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64" names="23" />
			</output>
		</layer>
		<layer id="18" name="ShapeOf_31624" 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="19" name="Constant_31625" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="20" name="Constant_31626" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="21" name="Gather_31627" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64" />
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="43,49,59,61" />
			</output>
		</layer>
		<layer id="22" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="67066584" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="23" name="__module.model.model.decoder/aten::arange/Range" type="Range" version="opset4">
			<data output_type="f32" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64" />
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="51,cache_position">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="24" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="FP32" names="52,position_ids">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="__module.model.model.decoder.embed_positions/aten::index/Convert" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<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="26" name="__module.model.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66492228" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="27" name="__module.model.model.decoder.embed_positions/aten::index/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>448</dim>
					<dim>1280</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="55,56,positions,positions.1">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="__module.model.model.decoder/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="57,input.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="29" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="31" name="Constant_31390" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="67066592" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="Constant_31391" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="67071712" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="90,hidden_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="Constant_31293" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="67076832" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="Convert_41326" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="Constant_31293/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="68715232" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="Constant_31293/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="Constant_31293/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="Multiply_31276" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="Constant_31392" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="68717792" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="__module.model.model.decoder.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="100,tensor.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="Constant_31709" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="102">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="103">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="68722960" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="Convert_41319" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="70361360" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="__module.model.model.decoder.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="106,tensor.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="Constant_31710" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="108">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="109">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="119,attn_weights.1">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="__module.model.model.decoder/aten::triu/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66492228" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="59" name="17" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="70363920" size="4" />
			<output>
				<port id="0" precision="FP32" names="17" />
			</output>
		</layer>
		<layer id="60" name="Constant_31648" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="Reshape_31649" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="__module.model.model.decoder/aten::add/Multiply_3" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="63" name="__module.model.model.decoder/aten::add/Add_3" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="62,64" />
			</output>
		</layer>
		<layer id="64" name="Constant_24084" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66492228" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="65" name="Unsqueeze_24085" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64" />
				<port id="1" precision="I32" />
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="__module.model.model.decoder/prim::ListConstruct_1" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="__module.model.model.decoder/aten::full/Broadcast" type="Broadcast" version="opset3">
			<data mode="numpy" />
			<input>
				<port id="0" precision="FP32" />
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="67">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="ShapeOf_31655" type="ShapeOf" version="opset3">
			<data output_type="i32" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I32">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="Constant_31656" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="70" name="Constant_31657" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="71" name="Gather_31658" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I32">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64" />
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I32" />
			</output>
		</layer>
		<layer id="72" name="__module.model.model.decoder/aten::triu/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="67066584" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="73" name="__module.model.model.decoder/aten::triu/Range" type="Range" version="opset4">
			<data output_type="i32" />
			<input>
				<port id="0" precision="I32" />
				<port id="1" precision="I32" />
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="I32">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="__module.model.model.decoder/aten::triu/Unsqueeze" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32" />
			</input>
			<output>
				<port id="2" precision="I32">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="__module.model.model.decoder/aten::triu/Convert" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="67066584" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="76" name="Convert_31661" type="Convert" version="opset1">
			<data destination_type="i32" />
			<input>
				<port id="0" precision="I64" />
			</input>
			<output>
				<port id="1" precision="I32" />
			</output>
		</layer>
		<layer id="77" name="__module.model.model.decoder/aten::triu/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I32" />
				<port id="1" precision="I32" />
			</input>
			<output>
				<port id="2" precision="I32" />
			</output>
		</layer>
		<layer id="78" name="__module.model.model.decoder/aten::triu/Range_1" type="Range" version="opset4">
			<data output_type="i32" />
			<input>
				<port id="0" precision="I32" />
				<port id="1" precision="I32" />
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="I32">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.model.model.decoder/aten::triu/Unsqueeze_1" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I32">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32" />
			</input>
			<output>
				<port id="2" precision="I32">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="__module.model.model.decoder/aten::triu/GreaterEqual" type="GreaterEqual" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I32">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I32">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="__module.model.model.decoder/aten::triu/ConvertLike" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="66492228" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="82" name="__module.model.model.decoder/aten::triu/Select" type="Select" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="2" precision="FP32" />
			</input>
			<output>
				<port id="3" precision="FP32" names="68_1">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="__module.model.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66492228" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="84" name="__module.model.model.decoder/aten::arange/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="67066584" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="85" name="__module.model.model.decoder/aten::arange/Range_1" type="Range" version="opset4">
			<data output_type="f32" />
			<input>
				<port id="0" precision="I32" />
				<port id="1" precision="I64" />
				<port id="2" precision="I32" />
			</input>
			<output>
				<port id="3" precision="FP32">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="__module.model.model.decoder/aten::arange/ConvertLike" type="Convert" version="opset1">
			<data destination_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64" names="69">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="__module.model.model.decoder/aten::gt/Convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="Constant_24187" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="70363924" size="16" />
			<output>
				<port id="0" precision="I64" names="70">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.model.model.decoder/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="71">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="72">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="__module.model.model.decoder/aten::mul_/ConvertLike" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="BOOL">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="__module.model.model.decoder/aten::mul_/Multiply" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="68,causal_mask.1">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="FP32" names="74">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="28" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64" names="28" />
			</output>
		</layer>
		<layer id="95" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_2" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="FP32" names="75,76,77">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="Constant_31639" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="Constant_31640" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="98" name="Gather_31641" 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="145,210,260,65,95">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="Constant_30625" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="Constant_30627" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="Constant_30629" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="__module.model.model.decoder/prim::ListConstruct_2" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="__module.model.model.decoder/aten::expand/Broadcast" type="Broadcast" version="opset3">
			<data mode="bidirectional" />
			<input>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="121,122,123,236,237,238,79,attention_mask">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="Constant_24621" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="ShapeOf_31670" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="Constant_31671" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="Constant_31672" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67066568" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="108" name="Gather_31673" 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="120,235">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="Constant_24624" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67066576" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="__module.model.model.decoder/aten::slice/Reshape_1" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="70363940" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="__module.model.model.decoder.layers.0.self_attn/aten::slice/Slice_3" type="Slice" version="opset8">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
				<port id="4" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="5" precision="FP32" names="124,239,causal_mask,causal_mask.5">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="__module.model.model.decoder.layers.0.self_attn/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</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="125,input.3">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="__module.model.model.decoder.layers.0.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="126,input.5">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="70363948" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="Convert_41312" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="72002348" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="Constant_31393" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="72004908" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="113,tensor.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="Constant_31711" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="115">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="124" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="116">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="128,attn_output.1">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</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="129,attn_output.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="Constant_31712" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="72010028" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="__module.model.model.decoder.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="131">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="72010052" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="Convert_41333" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="73648452" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="135" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="Constant_31394" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="73651012" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="134,input.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="__module.model.model.decoder.layers.0/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="136,residual.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="Constant_31395" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="73656132" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="Constant_31396" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="73661252" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="140,hidden_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="Constant_31296" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="73666372" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="Convert_41340" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="Constant_31296/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="75304772" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="Constant_31296/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="Constant_31296/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="Multiply_31280" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="Constant_31397" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="75307332" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="__module.model.model.decoder.layers.0.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="150,tensor.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="Constant_31713" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="152">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="153">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="75312452" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="159" name="Convert_41305" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="76950852" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="__module.model.model.decoder.layers.0.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="156,tensor.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="Constant_24369" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="76953412" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="Constant_24370" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="76953420" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="Constant_24371" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="76953428" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="__module.model.model.decoder.layers.0.self_attn/prim::ListConstruct_1" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
				<port id="3" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="168" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="158">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="159">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="171" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="169,input.9">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="__module.model.model.decoder.layers.0.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="170,input.11">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="76953436" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="Convert_41298" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="78591836" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="177" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="Constant_31398" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="78594396" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="180" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="163,tensor.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="181" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="165">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="166">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="172,attn_output.5">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</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="173,attn_output.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="Constant_31714" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="78599516" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="__module.model.model.decoder.layers.0.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="175">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="78599540" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="Convert_41347" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="80237940" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="193" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="Constant_31399" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="80240500" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="196" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="178,input.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.model.model.decoder.layers.0/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="180,residual.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="198" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="Constant_31400" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="80245620" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="201" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="Constant_31401" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="80250740" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="203" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="184">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="self.model.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
			<data element_type="i8" shape="5120, 1280" offset="80255860" size="6553600" />
			<output>
				<port id="0" precision="I8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="Convert_41256" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="self.model.model.decoder.layers.0.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 1" offset="86809460" size="10240" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="self.model.model.decoder.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="self.model.model.decoder.layers.0.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="__module.model.model.decoder.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="Constant_31402" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="86819700" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="__module.model.model.decoder.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="187">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="__module.model.model.decoder.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="188,input.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="self.model.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 5120" offset="86840180" size="6553600" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="214" name="Convert_41263" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="self.model.model.decoder.layers.0.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="93393780" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="self.model.model.decoder.layers.0.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="217" name="self.model.model.decoder.layers.0.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="218" name="__module.model.model.decoder.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="219" name="Constant_31403" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="93396340" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="__module.model.model.decoder.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="192,input.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="221" name="__module.model.model.decoder.layers.0/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="194,residual.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="222" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="Constant_31404" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="93401460" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="Constant_31405" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="93406580" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="205,hidden_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="Constant_31299" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="93411700" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="Convert_41368" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="230" name="Constant_31299/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="95050100" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="Constant_31299/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="Constant_31299/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="233" name="Multiply_31284" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="Constant_31406" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="95052660" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="235" name="__module.model.model.decoder.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="215,tensor.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="236" name="Constant_31715" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="217">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="239" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="218">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="95057780" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="Convert_41361" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="242" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="96696180" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="244" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="__module.model.model.decoder.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="221,tensor.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="Constant_31716" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="247" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="223">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="248" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="249" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="224">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="250" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="234,attn_weights">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="__module.model.model.decoder.layers.1.self_attn/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</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="240,input.19">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="252" name="__module.model.model.decoder.layers.1.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="241,input.21">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="253" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="96698740" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="254" name="Convert_41354" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="98337140" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="256" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="257" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="258" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="259" name="Constant_31407" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="98339700" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="228,tensor.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="Constant_31717" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</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>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="243,attn_output.9">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</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="244,attn_output.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="Constant_31718" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="72010028" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="269" name="__module.model.model.decoder.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="246">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="98344820" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="Convert_41375" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="272" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="99983220" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="Constant_31408" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="99985780" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="249,input.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="__module.model.model.decoder.layers.1/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="251,residual.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="281" name="Constant_31409" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="99990900" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="Constant_31410" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="99996020" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="255,hidden_states.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="Constant_31302" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="100001140" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="Convert_41382" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="287" name="Constant_31302/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="101639540" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="Constant_31302/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="289" name="Constant_31302/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="Multiply_31288" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="Constant_31411" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="101642100" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="__module.model.model.decoder.layers.1.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="265,tensor.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="Constant_31719" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="68722912" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="267">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="268">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="101647220" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="Convert_41291" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="103285620" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="301" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="__module.model.model.decoder.layers.1.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="271,tensor.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="273">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="305" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="274">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="284,input.25">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="__module.model.model.decoder.layers.1.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
			<data axis="-1" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="285,input.27">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="103288180" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="Convert_41284" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="104926580" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="313" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="Constant_31412" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="104929140" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="278,tensor">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="316" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="280">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="281">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="319" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="287,attn_output.13">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="320" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="68722944" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</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="288,attn_output">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="Constant_31720" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="78599516" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="323" name="__module.model.model.decoder.layers.1.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="290">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="324" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 1280" offset="104934260" size="1638400" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="325" name="Convert_41389" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="326" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="106572660" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="327" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="328" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="329" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="330" name="Constant_31413" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="106575220" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="331" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="293,input.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="332" name="__module.model.model.decoder.layers.1/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="295,residual">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="333" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="335" name="Constant_31414" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="106580340" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="Constant_31415" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="106585460" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="338" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="299">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="self.model.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
			<data element_type="i8" shape="5120, 1280" offset="106590580" size="6553600" />
			<output>
				<port id="0" precision="I8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="Convert_41270" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="self.model.model.decoder.layers.1.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 1" offset="113144180" size="10240" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="self.model.model.decoder.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="self.model.model.decoder.layers.1.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="344" name="__module.model.model.decoder.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="345" name="Constant_31416" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="113154420" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="346" name="__module.model.model.decoder.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="302">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="__module.model.model.decoder.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="303,input.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="348" name="self.model.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
			<data element_type="i8" shape="1280, 5120" offset="113174900" size="6553600" />
			<output>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="Convert_41277" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I8">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="350" name="self.model.model.decoder.layers.1.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 1" offset="119728500" size="2560" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="351" name="self.model.model.decoder.layers.1.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="self.model.model.decoder.layers.1.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="353" name="__module.model.model.decoder.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="Constant_31417" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="119731060" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="355" name="__module.model.model.decoder.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="307,input">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="__module.model.model.decoder.layers.1/aten::add/Add_2" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="309">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67066588" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="358" name="__module.model.model.decoder.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</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>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="Constant_31418" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="119736180" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="361" name="Constant_31419" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="119741300" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="362" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="313">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="363" name="__module.model.proj_out/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="logits">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51866</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="Result_26206" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51866</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="313" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="302" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="178" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="163" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="18" to-port="0" />
		<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
		<edge from-layer="3" from-port="1" to-layer="5" to-port="0" />
		<edge from-layer="4" from-port="0" to-layer="5" to-port="1" />
		<edge from-layer="5" from-port="2" to-layer="6" to-port="0" />
		<edge from-layer="6" from-port="1" to-layer="11" to-port="0" />
		<edge from-layer="6" from-port="1" to-layer="363" to-port="1" />
		<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
		<edge from-layer="8" from-port="2" to-layer="9" to-port="0" />
		<edge from-layer="9" from-port="1" to-layer="11" to-port="1" />
		<edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
		<edge from-layer="11" from-port="3" to-layer="28" to-port="0" />
		<edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
		<edge from-layer="13" from-port="1" to-layer="15" to-port="0" />
		<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
		<edge from-layer="15" from-port="2" to-layer="16" to-port="0" />
		<edge from-layer="16" from-port="1" to-layer="27" to-port="0" />
		<edge from-layer="17" from-port="0" to-layer="93" to-port="1" />
		<edge from-layer="17" from-port="0" to-layer="24" to-port="1" />
		<edge from-layer="17" from-port="0" to-layer="23" to-port="0" />
		<edge from-layer="18" from-port="1" to-layer="98" to-port="0" />
		<edge from-layer="18" from-port="1" to-layer="21" to-port="0" />
		<edge from-layer="19" from-port="0" to-layer="21" to-port="1" />
		<edge from-layer="20" from-port="0" to-layer="21" to-port="2" />
		<edge from-layer="21" from-port="3" to-layer="61" to-port="0" />
		<edge from-layer="21" from-port="3" to-layer="63" to-port="0" />
		<edge from-layer="21" from-port="3" to-layer="76" to-port="0" />
		<edge from-layer="21" from-port="3" to-layer="23" to-port="1" />
		<edge from-layer="22" from-port="0" to-layer="23" to-port="2" />
		<edge from-layer="23" from-port="3" to-layer="89" to-port="0" />
		<edge from-layer="23" from-port="3" to-layer="24" to-port="0" />
		<edge from-layer="24" from-port="2" to-layer="25" to-port="0" />
		<edge from-layer="25" from-port="1" to-layer="27" to-port="1" />
		<edge from-layer="26" from-port="0" to-layer="27" to-port="2" />
		<edge from-layer="27" from-port="3" to-layer="28" to-port="1" />
		<edge from-layer="28" from-port="2" to-layer="30" to-port="0" />
		<edge from-layer="28" from-port="2" to-layer="139" to-port="0" />
		<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
		<edge from-layer="30" from-port="2" to-layer="32" to-port="0" />
		<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
		<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
		<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
		<edge from-layer="34" from-port="2" to-layer="119" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="105" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="52" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="40" to-port="0" />
		<edge from-layer="35" from-port="0" to-layer="36" to-port="0" />
		<edge from-layer="36" from-port="1" to-layer="38" to-port="0" />
		<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
		<edge from-layer="38" from-port="2" to-layer="39" to-port="0" />
		<edge from-layer="39" from-port="1" to-layer="40" to-port="1" />
		<edge from-layer="40" from-port="2" to-layer="42" to-port="0" />
		<edge from-layer="41" from-port="0" to-layer="42" to-port="1" />
		<edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
		<edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
		<edge from-layer="44" from-port="2" to-layer="46" to-port="0" />
		<edge from-layer="45" from-port="0" to-layer="46" to-port="1" />
		<edge from-layer="46" from-port="2" to-layer="57" to-port="0" />
		<edge from-layer="47" from-port="0" to-layer="48" to-port="0" />
		<edge from-layer="48" from-port="1" to-layer="50" to-port="0" />
		<edge from-layer="49" from-port="0" to-layer="50" to-port="1" />
		<edge from-layer="50" from-port="2" to-layer="51" to-port="0" />
		<edge from-layer="51" from-port="1" to-layer="52" to-port="1" />
		<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
		<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
		<edge from-layer="54" from-port="2" to-layer="56" to-port="0" />
		<edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
		<edge from-layer="56" from-port="2" to-layer="57" to-port="1" />
		<edge from-layer="57" from-port="2" to-layer="112" to-port="0" />
		<edge from-layer="58" from-port="0" to-layer="73" to-port="0" />
		<edge from-layer="58" from-port="0" to-layer="74" to-port="1" />
		<edge from-layer="59" from-port="0" to-layer="67" to-port="0" />
		<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
		<edge from-layer="61" from-port="2" to-layer="66" 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="63" from-port="2" to-layer="85" to-port="1" />
		<edge from-layer="64" from-port="0" to-layer="65" to-port="1" />
		<edge from-layer="65" from-port="2" to-layer="66" to-port="1" />
		<edge from-layer="66" from-port="2" to-layer="67" to-port="1" />
		<edge from-layer="67" from-port="2" to-layer="82" to-port="1" />
		<edge from-layer="67" from-port="2" to-layer="68" to-port="0" />
		<edge from-layer="68" from-port="1" to-layer="71" to-port="0" />
		<edge from-layer="69" from-port="0" to-layer="71" to-port="1" />
		<edge from-layer="70" from-port="0" to-layer="71" to-port="2" />
		<edge from-layer="71" from-port="3" to-layer="73" to-port="1" />
		<edge from-layer="72" from-port="0" to-layer="73" to-port="2" />
		<edge from-layer="72" from-port="0" to-layer="79" to-port="1" />
		<edge from-layer="72" from-port="0" to-layer="78" to-port="2" />
		<edge from-layer="73" from-port="3" to-layer="74" to-port="0" />
		<edge from-layer="74" from-port="2" to-layer="80" to-port="0" />
		<edge from-layer="75" from-port="0" to-layer="78" to-port="0" />
		<edge from-layer="75" from-port="0" to-layer="77" to-port="1" />
		<edge from-layer="76" from-port="1" to-layer="77" to-port="0" />
		<edge from-layer="77" from-port="2" to-layer="78" to-port="1" />
		<edge from-layer="78" from-port="3" to-layer="79" to-port="0" />
		<edge from-layer="79" from-port="2" to-layer="80" to-port="1" />
		<edge from-layer="80" from-port="2" to-layer="82" to-port="0" />
		<edge from-layer="81" from-port="0" to-layer="82" to-port="2" />
		<edge from-layer="82" from-port="3" to-layer="92" to-port="0" />
		<edge from-layer="83" from-port="0" to-layer="85" to-port="0" />
		<edge from-layer="84" from-port="0" to-layer="85" to-port="2" />
		<edge from-layer="85" from-port="3" to-layer="86" to-port="0" />
		<edge from-layer="86" from-port="1" to-layer="87" to-port="0" />
		<edge from-layer="87" from-port="1" to-layer="90" 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="1" />
		<edge from-layer="90" from-port="2" to-layer="91" to-port="0" />
		<edge from-layer="91" from-port="1" to-layer="92" to-port="1" />
		<edge from-layer="92" from-port="2" to-layer="93" to-port="0" />
		<edge from-layer="93" from-port="2" to-layer="95" to-port="0" />
		<edge from-layer="94" from-port="0" to-layer="95" to-port="1" />
		<edge from-layer="95" from-port="2" to-layer="103" to-port="0" />
		<edge from-layer="96" from-port="0" to-layer="98" to-port="1" />
		<edge from-layer="97" from-port="0" to-layer="98" to-port="2" />
		<edge from-layer="98" from-port="3" to-layer="102" to-port="0" />
		<edge from-layer="98" from-port="3" to-layer="167" to-port="0" />
		<edge from-layer="99" from-port="0" to-layer="102" to-port="1" />
		<edge from-layer="100" from-port="0" to-layer="102" to-port="2" />
		<edge from-layer="101" from-port="0" to-layer="102" to-port="3" />
		<edge from-layer="102" from-port="4" to-layer="103" to-port="1" />
		<edge from-layer="103" from-port="2" to-layer="111" to-port="0" />
		<edge from-layer="104" from-port="0" to-layer="111" to-port="1" />
		<edge from-layer="105" from-port="1" to-layer="108" to-port="0" />
		<edge from-layer="106" from-port="0" to-layer="108" to-port="1" />
		<edge from-layer="107" from-port="0" to-layer="108" to-port="2" />
		<edge from-layer="108" from-port="3" to-layer="111" to-port="2" />
		<edge from-layer="109" from-port="0" to-layer="111" to-port="3" />
		<edge from-layer="110" from-port="0" to-layer="111" to-port="4" />
		<edge from-layer="111" from-port="5" to-layer="251" to-port="1" />
		<edge from-layer="111" from-port="5" to-layer="112" to-port="1" />
		<edge from-layer="112" from-port="2" to-layer="113" to-port="0" />
		<edge from-layer="113" from-port="1" to-layer="126" to-port="0" />
		<edge from-layer="114" from-port="0" to-layer="115" to-port="0" />
		<edge from-layer="115" from-port="1" 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="118" to-port="0" />
		<edge from-layer="118" from-port="1" to-layer="119" to-port="1" />
		<edge from-layer="119" from-port="2" to-layer="121" to-port="0" />
		<edge from-layer="120" from-port="0" to-layer="121" to-port="1" />
		<edge from-layer="121" from-port="2" to-layer="123" to-port="0" />
		<edge from-layer="122" from-port="0" to-layer="123" to-port="1" />
		<edge from-layer="123" from-port="2" to-layer="125" to-port="0" />
		<edge from-layer="124" from-port="0" to-layer="125" to-port="1" />
		<edge from-layer="125" from-port="2" to-layer="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="136" to-port="0" />
		<edge from-layer="131" from-port="0" to-layer="132" to-port="0" />
		<edge from-layer="132" from-port="1" to-layer="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="135" to-port="0" />
		<edge from-layer="135" from-port="1" 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="1" />
		<edge from-layer="139" from-port="2" to-layer="197" to-port="0" />
		<edge from-layer="139" from-port="2" to-layer="141" to-port="0" />
		<edge from-layer="140" from-port="0" to-layer="141" to-port="1" />
		<edge from-layer="141" from-port="2" to-layer="143" to-port="0" />
		<edge from-layer="142" from-port="0" to-layer="143" to-port="1" />
		<edge from-layer="143" from-port="2" to-layer="145" to-port="0" />
		<edge from-layer="144" from-port="0" to-layer="145" to-port="1" />
		<edge from-layer="145" from-port="2" to-layer="151" to-port="0" />
		<edge from-layer="146" from-port="0" to-layer="147" to-port="0" />
		<edge from-layer="147" from-port="1" to-layer="149" to-port="0" />
		<edge from-layer="148" from-port="0" to-layer="149" to-port="1" />
		<edge from-layer="149" from-port="2" to-layer="150" to-port="0" />
		<edge from-layer="150" from-port="1" 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="155" to-port="0" />
		<edge from-layer="154" from-port="0" to-layer="155" to-port="1" />
		<edge from-layer="155" from-port="2" to-layer="157" to-port="0" />
		<edge from-layer="156" from-port="0" to-layer="157" to-port="1" />
		<edge from-layer="157" from-port="2" to-layer="171" to-port="0" />
		<edge from-layer="158" from-port="0" to-layer="159" to-port="0" />
		<edge from-layer="159" from-port="1" to-layer="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="162" to-port="0" />
		<edge from-layer="162" from-port="1" to-layer="163" to-port="1" />
		<edge from-layer="163" from-port="2" to-layer="168" to-port="0" />
		<edge from-layer="164" from-port="0" to-layer="167" to-port="1" />
		<edge from-layer="165" from-port="0" to-layer="167" to-port="2" />
		<edge from-layer="166" from-port="0" to-layer="167" to-port="3" />
		<edge from-layer="167" from-port="4" to-layer="168" to-port="1" />
		<edge from-layer="167" from-port="4" to-layer="303" to-port="1" />
		<edge from-layer="167" from-port="4" to-layer="316" to-port="1" />
		<edge from-layer="167" from-port="4" to-layer="181" to-port="1" />
		<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="171" to-port="1" />
		<edge from-layer="171" from-port="2" to-layer="172" to-port="0" />
		<edge from-layer="172" from-port="1" to-layer="184" to-port="0" />
		<edge from-layer="173" from-port="0" to-layer="174" to-port="0" />
		<edge from-layer="174" from-port="1" to-layer="176" to-port="0" />
		<edge from-layer="175" from-port="0" to-layer="176" to-port="1" />
		<edge from-layer="176" from-port="2" to-layer="177" to-port="0" />
		<edge from-layer="177" from-port="1" to-layer="178" to-port="1" />
		<edge from-layer="178" from-port="2" to-layer="180" to-port="0" />
		<edge from-layer="179" from-port="0" to-layer="180" to-port="1" />
		<edge from-layer="180" from-port="2" to-layer="181" to-port="0" />
		<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="186" to-port="0" />
		<edge from-layer="185" from-port="0" to-layer="186" to-port="1" />
		<edge from-layer="186" from-port="2" to-layer="188" to-port="0" />
		<edge from-layer="187" from-port="0" to-layer="188" to-port="1" />
		<edge from-layer="188" from-port="2" to-layer="194" to-port="0" />
		<edge from-layer="189" from-port="0" to-layer="190" to-port="0" />
		<edge from-layer="190" from-port="1" to-layer="192" to-port="0" />
		<edge from-layer="191" from-port="0" to-layer="192" to-port="1" />
		<edge from-layer="192" from-port="2" to-layer="193" to-port="0" />
		<edge from-layer="193" from-port="1" to-layer="194" to-port="1" />
		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
		<edge from-layer="195" from-port="0" to-layer="196" to-port="1" />
		<edge from-layer="196" from-port="2" to-layer="197" to-port="1" />
		<edge from-layer="197" from-port="2" to-layer="221" to-port="0" />
		<edge from-layer="197" from-port="2" to-layer="199" to-port="0" />
		<edge from-layer="198" from-port="0" to-layer="199" to-port="1" />
		<edge from-layer="199" from-port="2" to-layer="201" to-port="0" />
		<edge from-layer="200" from-port="0" to-layer="201" to-port="1" />
		<edge from-layer="201" from-port="2" to-layer="203" to-port="0" />
		<edge from-layer="202" from-port="0" to-layer="203" to-port="1" />
		<edge from-layer="203" from-port="2" to-layer="209" to-port="0" />
		<edge from-layer="204" from-port="0" to-layer="205" to-port="0" />
		<edge from-layer="205" from-port="1" to-layer="207" to-port="0" />
		<edge from-layer="206" from-port="0" to-layer="207" to-port="1" />
		<edge from-layer="207" from-port="2" to-layer="208" to-port="0" />
		<edge from-layer="208" from-port="1" to-layer="209" to-port="1" />
		<edge from-layer="209" from-port="2" to-layer="211" to-port="0" />
		<edge from-layer="210" from-port="0" to-layer="211" to-port="1" />
		<edge from-layer="211" from-port="2" to-layer="212" to-port="0" />
		<edge from-layer="212" from-port="1" to-layer="218" to-port="0" />
		<edge from-layer="213" from-port="0" to-layer="214" to-port="0" />
		<edge from-layer="214" from-port="1" to-layer="216" to-port="0" />
		<edge from-layer="215" from-port="0" to-layer="216" to-port="1" />
		<edge from-layer="216" from-port="2" to-layer="217" to-port="0" />
		<edge from-layer="217" from-port="1" to-layer="218" to-port="1" />
		<edge from-layer="218" from-port="2" to-layer="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="221" to-port="1" />
		<edge from-layer="221" from-port="2" to-layer="278" to-port="0" />
		<edge from-layer="221" from-port="2" to-layer="223" to-port="0" />
		<edge from-layer="222" from-port="0" to-layer="223" to-port="1" />
		<edge from-layer="223" from-port="2" to-layer="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="233" to-port="0" />
		<edge from-layer="227" from-port="2" to-layer="258" to-port="0" />
		<edge from-layer="227" from-port="2" to-layer="245" to-port="0" />
		<edge from-layer="228" from-port="0" to-layer="229" to-port="0" />
		<edge from-layer="229" from-port="1" to-layer="231" to-port="0" />
		<edge from-layer="230" from-port="0" to-layer="231" to-port="1" />
		<edge from-layer="231" from-port="2" to-layer="232" to-port="0" />
		<edge from-layer="232" from-port="1" 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="250" to-port="0" />
		<edge from-layer="240" from-port="0" to-layer="241" to-port="0" />
		<edge from-layer="241" from-port="1" 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="244" to-port="0" />
		<edge from-layer="244" from-port="1" to-layer="245" to-port="1" />
		<edge from-layer="245" from-port="2" to-layer="247" to-port="0" />
		<edge from-layer="246" from-port="0" to-layer="247" to-port="1" />
		<edge from-layer="247" from-port="2" to-layer="249" to-port="0" />
		<edge from-layer="248" from-port="0" to-layer="249" to-port="1" />
		<edge from-layer="249" from-port="2" to-layer="250" to-port="1" />
		<edge from-layer="250" from-port="2" to-layer="251" to-port="0" />
		<edge from-layer="251" from-port="2" to-layer="252" to-port="0" />
		<edge from-layer="252" from-port="1" to-layer="265" to-port="0" />
		<edge from-layer="253" from-port="0" to-layer="254" to-port="0" />
		<edge from-layer="254" from-port="1" to-layer="256" to-port="0" />
		<edge from-layer="255" from-port="0" to-layer="256" to-port="1" />
		<edge from-layer="256" from-port="2" to-layer="257" to-port="0" />
		<edge from-layer="257" from-port="1" to-layer="258" to-port="1" />
		<edge from-layer="258" from-port="2" to-layer="260" to-port="0" />
		<edge from-layer="259" from-port="0" to-layer="260" to-port="1" />
		<edge from-layer="260" from-port="2" to-layer="262" to-port="0" />
		<edge from-layer="261" from-port="0" to-layer="262" to-port="1" />
		<edge from-layer="262" from-port="2" to-layer="264" to-port="0" />
		<edge from-layer="263" from-port="0" to-layer="264" to-port="1" />
		<edge from-layer="264" from-port="2" to-layer="265" to-port="1" />
		<edge from-layer="265" from-port="2" to-layer="267" to-port="0" />
		<edge from-layer="266" from-port="0" to-layer="267" to-port="1" />
		<edge from-layer="267" from-port="2" to-layer="269" to-port="0" />
		<edge from-layer="268" from-port="0" to-layer="269" to-port="1" />
		<edge from-layer="269" from-port="2" to-layer="275" to-port="0" />
		<edge from-layer="270" from-port="0" to-layer="271" to-port="0" />
		<edge from-layer="271" from-port="1" 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="274" to-port="0" />
		<edge from-layer="274" from-port="1" to-layer="275" to-port="1" />
		<edge from-layer="275" from-port="2" to-layer="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="278" to-port="1" />
		<edge from-layer="278" from-port="2" to-layer="280" to-port="0" />
		<edge from-layer="278" from-port="2" to-layer="332" to-port="0" />
		<edge from-layer="279" from-port="0" to-layer="280" to-port="1" />
		<edge from-layer="280" from-port="2" to-layer="282" to-port="0" />
		<edge from-layer="281" from-port="0" to-layer="282" to-port="1" />
		<edge from-layer="282" from-port="2" 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="290" to-port="0" />
		<edge from-layer="285" from-port="0" to-layer="286" to-port="0" />
		<edge from-layer="286" from-port="1" to-layer="288" to-port="0" />
		<edge from-layer="287" from-port="0" to-layer="288" to-port="1" />
		<edge from-layer="288" from-port="2" to-layer="289" to-port="0" />
		<edge from-layer="289" from-port="1" to-layer="290" to-port="1" />
		<edge from-layer="290" from-port="2" to-layer="292" to-port="0" />
		<edge from-layer="291" from-port="0" to-layer="292" to-port="1" />
		<edge from-layer="292" from-port="2" to-layer="294" to-port="0" />
		<edge from-layer="293" from-port="0" to-layer="294" to-port="1" />
		<edge from-layer="294" from-port="2" to-layer="296" to-port="0" />
		<edge from-layer="295" from-port="0" to-layer="296" to-port="1" />
		<edge from-layer="296" from-port="2" to-layer="306" to-port="0" />
		<edge from-layer="297" from-port="0" to-layer="298" to-port="0" />
		<edge from-layer="298" from-port="1" to-layer="300" to-port="0" />
		<edge from-layer="299" from-port="0" to-layer="300" to-port="1" />
		<edge from-layer="300" from-port="2" to-layer="301" to-port="0" />
		<edge from-layer="301" from-port="1" to-layer="302" to-port="1" />
		<edge from-layer="302" from-port="2" to-layer="303" to-port="0" />
		<edge from-layer="303" from-port="2" to-layer="305" to-port="0" />
		<edge from-layer="304" from-port="0" to-layer="305" to-port="1" />
		<edge from-layer="305" from-port="2" to-layer="306" to-port="1" />
		<edge from-layer="306" from-port="2" to-layer="307" to-port="0" />
		<edge from-layer="307" from-port="1" to-layer="319" to-port="0" />
		<edge from-layer="308" from-port="0" to-layer="309" to-port="0" />
		<edge from-layer="309" from-port="1" to-layer="311" to-port="0" />
		<edge from-layer="310" from-port="0" to-layer="311" to-port="1" />
		<edge from-layer="311" from-port="2" to-layer="312" to-port="0" />
		<edge from-layer="312" from-port="1" to-layer="313" to-port="1" />
		<edge from-layer="313" from-port="2" to-layer="315" to-port="0" />
		<edge from-layer="314" from-port="0" to-layer="315" to-port="1" />
		<edge from-layer="315" from-port="2" to-layer="316" to-port="0" />
		<edge from-layer="316" from-port="2" to-layer="318" to-port="0" />
		<edge from-layer="317" from-port="0" to-layer="318" to-port="1" />
		<edge from-layer="318" from-port="2" 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="329" to-port="0" />
		<edge from-layer="324" from-port="0" to-layer="325" to-port="0" />
		<edge from-layer="325" from-port="1" to-layer="327" to-port="0" />
		<edge from-layer="326" from-port="0" to-layer="327" to-port="1" />
		<edge from-layer="327" from-port="2" to-layer="328" to-port="0" />
		<edge from-layer="328" from-port="1" to-layer="329" to-port="1" />
		<edge from-layer="329" from-port="2" to-layer="331" to-port="0" />
		<edge from-layer="330" from-port="0" to-layer="331" to-port="1" />
		<edge from-layer="331" from-port="2" to-layer="332" to-port="1" />
		<edge from-layer="332" from-port="2" to-layer="334" to-port="0" />
		<edge from-layer="332" from-port="2" to-layer="356" 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="336" to-port="0" />
		<edge from-layer="335" from-port="0" to-layer="336" to-port="1" />
		<edge from-layer="336" from-port="2" to-layer="338" to-port="0" />
		<edge from-layer="337" from-port="0" to-layer="338" to-port="1" />
		<edge from-layer="338" from-port="2" to-layer="344" to-port="0" />
		<edge from-layer="339" from-port="0" to-layer="340" to-port="0" />
		<edge from-layer="340" from-port="1" to-layer="342" to-port="0" />
		<edge from-layer="341" from-port="0" to-layer="342" to-port="1" />
		<edge from-layer="342" from-port="2" to-layer="343" to-port="0" />
		<edge from-layer="343" from-port="1" to-layer="344" to-port="1" />
		<edge from-layer="344" from-port="2" to-layer="346" to-port="0" />
		<edge from-layer="345" from-port="0" to-layer="346" to-port="1" />
		<edge from-layer="346" from-port="2" to-layer="347" to-port="0" />
		<edge from-layer="347" from-port="1" to-layer="353" to-port="0" />
		<edge from-layer="348" from-port="0" to-layer="349" to-port="0" />
		<edge from-layer="349" from-port="1" to-layer="351" to-port="0" />
		<edge from-layer="350" from-port="0" to-layer="351" to-port="1" />
		<edge from-layer="351" from-port="2" to-layer="352" to-port="0" />
		<edge from-layer="352" from-port="1" 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="356" to-port="1" />
		<edge from-layer="356" from-port="2" to-layer="358" to-port="0" />
		<edge from-layer="357" from-port="0" to-layer="358" to-port="1" />
		<edge from-layer="358" from-port="2" to-layer="360" to-port="0" />
		<edge from-layer="359" from-port="0" to-layer="360" to-port="1" />
		<edge from-layer="360" from-port="2" to-layer="362" to-port="0" />
		<edge from-layer="361" from-port="0" to-layer="362" to-port="1" />
		<edge from-layer="362" from-port="2" to-layer="363" to-port="0" />
		<edge from-layer="363" from-port="2" to-layer="364" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2024.6.0-17404-4c0f47d2335-releases/2024/6" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<nncf>
			<friendly_names_were_updated value="True" />
			<weight_compression>
				<advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
				<all_layers value="False" />
				<awq value="False" />
				<backup_mode value="int8_asym" />
				<gptq value="False" />
				<group_size value="-1" />
				<ignored_scope value="[]" />
				<lora_correction value="False" />
				<mode value="int8_sym" />
				<ratio value="1" />
				<scale_estimation value="False" />
				<sensitivity_metric value="weight_quantization_error" />
			</weight_compression>
		</nncf>
		<optimum>
			<optimum_intel_version value="1.21.0" />
			<optimum_version value="1.23.3" />
			<pytorch_version value="2.4.0" />
			<transformers_version value="4.46.0" />
		</optimum>
	</rt_info>
</net>