openvino_decoder_with_past_model.xml

<?xml version="1.0"?>
<net name="Model6" version="11">
	<layers>
		<layer id="18" name="decoder_input_ids" type="Parameter" version="opset1">
			<data shape="?,1" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="input_ids">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="encoder_outputs" type="Parameter" version="opset1">
			<data shape="?,?,1280" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="encoder_hidden_states">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="Parameter_38680" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.0.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="Parameter_38679" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.0.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="Parameter_38678" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.0.encoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="Parameter_38677" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.0.encoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="Parameter_38684" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.1.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="Parameter_38683" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.1.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="Parameter_38682" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.1.encoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="Parameter_38681" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.1.encoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="Parameter_38688" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.2.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="Parameter_38687" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.2.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="Parameter_38686" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.2.encoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="Parameter_38685" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.2.encoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Parameter_38692" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.3.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="Parameter_38691" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.3.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="Parameter_38690" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.3.encoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="Parameter_38689" type="Parameter" version="opset1">
			<data shape="?,20,?,64" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="past_key_values.3.encoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="0" name="cache_position" type="Parameter" version="opset1">
			<data shape="?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="cache_position">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="self.model.model.decoder.embed_tokens.weight" type="Const" version="opset1">
			<data element_type="u8" shape="51866, 1280" offset="0" size="66388480" />
			<output>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="20" name="Convert_1078432" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<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="21" name="self.model.model.decoder.embed_tokens.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="51866, 1" offset="66388480" size="51866" />
			<output>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="Convert_1078435" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="self.model.model.decoder.embed_tokens.weight/zero_point/subtract" type="Subtract" 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="24" name="self.model.model.decoder.embed_tokens.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="51866, 1" offset="66440346" size="103732" />
			<output>
				<port id="0" precision="FP16">
					<dim>51866</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="25" 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="26" 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="27" name="__module.model.model.decoder/prim::ListConstruct" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="66544078" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="28" 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="88,input.1">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="29" 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="30" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66544094" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="31" 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="90,inputs_embeds">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="self.model.model.decoder.embed_positions.weight" type="Const" version="opset1">
			<data element_type="u8" shape="448, 1280" offset="66544098" size="573440" />
			<output>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="Convert_1220295" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<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="34" name="self.model.model.decoder.embed_positions.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="448, 1" offset="67117538" size="448" />
			<output>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="Convert_1220298" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="self.model.model.decoder.embed_positions.weight/zero_point/subtract" type="Subtract" 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="37" name="self.model.model.decoder.embed_positions.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="448, 1" offset="67117986" size="896" />
			<output>
				<port id="0" precision="FP16">
					<dim>448</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="38" 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="39" 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="40" name="60" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64" names="60" />
			</output>
		</layer>
		<layer id="41" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64" />
			</input>
			<output>
				<port id="2" precision="I64" names="91">
					<dim>1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="ShapeOf_46188" 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="43" name="Constant_46189" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="Constant_46190" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="45" name="Gather_46191" 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="108,137,241,342,443,85">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="Constant_39005" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="__module.model.model.decoder/prim::ListConstruct/Concat" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="92">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="__module.model.model.decoder/aten::repeat/Tile" type="Tile" version="opset1">
			<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="93,position_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="__module.model.model.decoder.embed_positions/aten::index/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="50" name="__module.model.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66544094" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="51" 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="96,97,positions,positions.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="__module.model.model.decoder/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="98,input.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="53" 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="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="54" 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="55" name="Constant_45721" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="67118902" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="56" 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="57" name="Constant_45722" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="67124022" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="58" 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="132,hidden_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="67129142" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="60" name="Convert_1125719" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="67948342" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="Convert_1125722" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="67954742" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Constant_1125727" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="Reshape_1125728" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="self.model.model.decoder.layers.0.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="__module.model.model.decoder.layers.0.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="70" name="Constant_45723" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="67980358" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="__module.model.model.decoder.layers.0.self_attn.q_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="141">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="Constant_46568" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="73" 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="143,query_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="75" 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="144">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="67985526" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="Convert_1121420" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="68804726" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="Convert_1121423" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="68811126" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="82" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="Constant_1121428" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="Reshape_1121429" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="85" 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="86" 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="147">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="Constant_46569" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="88" 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="149,key_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="90" 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="155">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="__module.model.model.decoder.layers.0.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.0.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="68836726" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="Convert_1117121" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="69655926" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="Convert_1117124" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="69662326" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="98" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="Constant_1117129" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="Reshape_1117130" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="101" 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="102" 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="103" name="Constant_45724" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="69687926" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="104" 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="152">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="Constant_46570" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="106" 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="154,value_states.1">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_2" 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="157">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="__module.model.model.decoder.layers.0.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.0.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="Constant_45725" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1" offset="69693046" size="4" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66544094" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="112" name="ShapeOf_46204" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="Constant_46205" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="69693050" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="114" name="Constant_46206" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="115" name="Gather_46207" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
				<port id="1" precision="I64" />
				<port id="2" precision="I64" />
			</input>
			<output>
				<port id="3" precision="I64" names="100" />
			</output>
		</layer>
		<layer id="116" name="Constant_46213" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="117" name="Constant_46214" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="118" name="Gather_46215" 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="102" />
			</output>
		</layer>
		<layer id="119" name="__module.model.model.decoder/aten::add/Add_1" 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="104" />
			</output>
		</layer>
		<layer id="120" name="__module.model.model.decoder/aten::add/Multiply_2" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="121" name="__module.model.model.decoder/aten::add/Add_2" 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="105,107,target_length" />
			</output>
		</layer>
		<layer id="122" name="__module.model.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="69693058" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="123" name="__module.model.model.decoder/aten::arange/Range" 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="124" 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="111">
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="Constant_36680" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="69693062" size="16" />
			<output>
				<port id="0" precision="I64" names="112">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="__module.model.model.decoder/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64" names="113">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>-1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="BOOL" names="114">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="128" 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="129" name="Multiply_44061" 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">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="ShapeOf_44062" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="Constant_46218" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="Reshape_46219" 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="133" name="Constant_36666" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="66544094" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="134" name="Unsqueeze_36667" 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="135" 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="136" name="Maximum_44063" type="Maximum" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="__module.model.model.decoder/aten::mul_/Multiply" type="Broadcast" version="opset3">
			<data mode="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="110,causal_mask.1">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="138" 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="116">
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="61" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64" names="61" />
			</output>
		</layer>
		<layer id="140" 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="117,118,119">
					<dim>1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="Constant_43426" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="Constant_43428" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="Constant_43430" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="144" 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="145" 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="121,167,168,169,268,269,270,369,370,371,470,471,472,attention_mask">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="Constant_36963" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="Constant_46226" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="Reshape_46227" 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="149" name="ShapeOf_46228" 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="150" name="Constant_46229" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="Constant_46230" type="Const" version="opset1">
			<data element_type="i64" shape="" offset="67118882" size="8" />
			<output>
				<port id="0" precision="I64" />
			</output>
		</layer>
		<layer id="152" name="Gather_46231" 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">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="Add_46232" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<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" names="166,267,368,469">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="Constant_36966" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="67118890" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="Constant_36961" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="69693078" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="156" 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="170,271,372,473,causal_mask,causal_mask.5,causal_mask.7,causal_mask.9">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="__module.model.model.decoder.layers.0.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="FP32" names="171,attn_output.1">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="159" 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>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="172,attn_output.3">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="Constant_46571" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="161" 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="174,input.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="69693110" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="Convert_1130018" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="70512310" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="Convert_1130021" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="70518710" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="168" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="Constant_1130026" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="Reshape_1130027" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="171" 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="172" 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="173" name="Constant_45726" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="70544310" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="174" 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="177,179,input.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="175" 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="183,input.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="176" 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="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="177" 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="178" name="Constant_45727" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="70549430" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="179" 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="180" name="Constant_45728" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="70554550" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="181" 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="187,hidden_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="70559670" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="Convert_1134317" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="71378870" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="Convert_1134320" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="71385270" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="self.model.model.decoder.layers.0.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="Constant_1134325" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="Reshape_1134326" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="self.model.model.decoder.layers.0.encoder_attn.q_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="192" name="__module.model.model.decoder.layers.0.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="193" name="Constant_45729" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="71410870" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="__module.model.model.decoder.layers.0.encoder_attn.q_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="194">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="Constant_46572" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="196" 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="196,query_states.5">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="198" 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="197">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="__module.model.model.decoder.layers.0.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="199,attn_output.5">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="201" 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>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="200,attn_output.7">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="Constant_46573" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="203" 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="202,input.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="71415990" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="Convert_1138616" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="72235190" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="Convert_1138619" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="72241590" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="210" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="Constant_1138624" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="Reshape_1138625" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="213" 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="214" 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="215" name="Constant_45730" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="72267190" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="216" 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="205,input.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="217" 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="207,input.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="218" 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="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="219" 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="220" name="Constant_45731" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="72272310" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="221" 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="222" name="Constant_45732" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="72277430" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="223" 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="211,input.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="self.model.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 128" offset="72282550" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="Convert_1082729" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="self.model.model.decoder.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 1" offset="75559350" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="Convert_1082732" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="self.model.model.decoder.layers.0.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="self.model.model.decoder.layers.0.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 10, 1" offset="75584950" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="230" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="Constant_1082737" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="75687350" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="Reshape_1082738" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="233" 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="234" 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="235" name="Constant_45733" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="75687366" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="236" 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="214,input.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="237" 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="215,input.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="self.model.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 128" offset="75707846" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="239" name="Convert_1087028" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="self.model.model.decoder.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 1" offset="78984646" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="Convert_1087031" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="242" name="self.model.model.decoder.layers.0.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="self.model.model.decoder.layers.0.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 40, 1" offset="79010246" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="244" 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>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="Constant_1087036" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="79112646" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="Reshape_1087037" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="247" 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="248" 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="249" name="Constant_45734" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="79112662" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="250" 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="219,input.27">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="251" 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="221,223,input.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="252" 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="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="253" 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="254" name="Constant_45735" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="79117782" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="255" 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="256" name="Constant_45736" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="79122902" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="257" 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="236,hidden_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="258" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="79128022" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="259" name="Convert_1151513" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="79947222" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="Convert_1151516" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="79953622" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="Constant_1151521" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="Reshape_1151522" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="self.model.model.decoder.layers.1.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="__module.model.model.decoder.layers.1.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="269" name="Constant_45737" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="79979222" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="__module.model.model.decoder.layers.1.self_attn.q_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="245">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="Constant_46574" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="272" 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="247,query_states.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="274" 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="248">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="79984342" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="Convert_1147214" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="80803542" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="Convert_1147217" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="80809942" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="281" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="Constant_1147222" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="Reshape_1147223" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="284" 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="285" 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="251">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="Constant_46575" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="287" 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="253,key_states.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="289" 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="259">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="__module.model.model.decoder.layers.1.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.1.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="80835542" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="Convert_1142915" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="81654742" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="Convert_1142918" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="81661142" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="297" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="Constant_1142923" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="Reshape_1142924" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="300" 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="301" 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="302" name="Constant_45738" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="81686742" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="303" 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="256">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="Constant_46576" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="305" 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="258,value_states.9">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_2" 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="261">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="__module.model.model.decoder.layers.1.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.1.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="__module.model.model.decoder.layers.1.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="FP32" names="272,attn_output.9">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="311" 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>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="273,attn_output.11">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="Constant_46577" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="313" 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="275,input.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="81691862" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="Convert_1155812" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="316" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="82511062" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="Convert_1155815" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="319" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="82517462" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="320" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="Constant_1155820" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="Reshape_1155821" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="323" 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="324" 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="325" name="Constant_45739" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="82543062" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="326" 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="278,280,input.33">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="327" 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="284,input.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="328" 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="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="329" 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="330" name="Constant_45740" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="82548182" 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_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="332" name="Constant_45741" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="82553302" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="333" 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="288,hidden_states.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="82558422" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="335" name="Convert_1160111" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="83377622" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="Convert_1160114" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="338" name="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="83384022" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="self.model.model.decoder.layers.1.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="Constant_1160119" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="Reshape_1160120" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="self.model.model.decoder.layers.1.encoder_attn.q_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="344" name="__module.model.model.decoder.layers.1.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="345" name="Constant_45742" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="83409622" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="346" name="__module.model.model.decoder.layers.1.encoder_attn.q_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="295">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="Constant_46578" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="348" 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="297,query_states.13">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="350" 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="298">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="351" name="__module.model.model.decoder.layers.1.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="300,attn_output.13">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="353" 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>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="301,attn_output.15">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="Constant_46579" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="355" 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="303,input.37">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="83414742" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="Convert_1164410" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="358" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="84233942" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="Convert_1164413" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="361" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="84240342" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="362" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="363" name="Constant_1164418" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="Reshape_1164419" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="365" 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="366" 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="367" name="Constant_45743" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="84265942" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="368" 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="306,input.39">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="369" 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="308,input.41">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="370" 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="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="371" 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="372" name="Constant_45744" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="84271062" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="373" 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="374" name="Constant_45745" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="84276182" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="375" 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="312,input.43">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="376" name="self.model.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 128" offset="84281302" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="377" name="Convert_1091327" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="378" name="self.model.model.decoder.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 1" offset="87558102" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="379" name="Convert_1091330" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="380" name="self.model.model.decoder.layers.1.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="381" name="self.model.model.decoder.layers.1.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 10, 1" offset="87583702" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="382" 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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="383" name="Constant_1091335" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="75687350" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="384" name="Reshape_1091336" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="385" 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="386" 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="387" name="Constant_45746" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="87686102" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="388" 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="315,input.45">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="389" 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="316,input.47">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="390" name="self.model.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 128" offset="87706582" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="391" name="Convert_1095626" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="392" name="self.model.model.decoder.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 1" offset="90983382" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="393" name="Convert_1095629" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="394" name="self.model.model.decoder.layers.1.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="395" name="self.model.model.decoder.layers.1.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 40, 1" offset="91008982" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="396" 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>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="397" name="Constant_1095634" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="79112646" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="398" name="Reshape_1095635" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="399" 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="400" 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="401" name="Constant_45747" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="91111382" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="402" 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="320,input.51">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="403" 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="322,324,input.53">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="404" name="__module.model.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="405" name="__module.model.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="406" name="Constant_45748" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="91116502" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="407" name="__module.model.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="408" name="Constant_45749" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="91121622" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="409" name="__module.model.model.decoder.layers.2.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="337,hidden_states.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="410" name="self.model.model.decoder.layers.2.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="91126742" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="411" name="Convert_1177307" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="412" name="self.model.model.decoder.layers.2.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="91945942" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="413" name="Convert_1177310" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="414" name="self.model.model.decoder.layers.2.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="415" name="self.model.model.decoder.layers.2.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="91952342" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="416" name="self.model.model.decoder.layers.2.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="417" name="Constant_1177315" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="418" name="Reshape_1177316" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="419" name="self.model.model.decoder.layers.2.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="420" name="__module.model.model.decoder.layers.2.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="421" name="Constant_45750" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="91977942" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="422" name="__module.model.model.decoder.layers.2.self_attn.q_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="346">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="423" name="Constant_46580" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="424" name="__module.model.model.decoder.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="348,query_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="425" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="426" name="__module.model.model.decoder.layers.2.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="349">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="427" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="91983062" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="428" name="Convert_1173008" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="429" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="92802262" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="430" name="Convert_1173011" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="431" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="432" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="92808662" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="433" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="434" name="Constant_1173016" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="435" name="Reshape_1173017" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="436" name="self.model.model.decoder.layers.2.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="437" name="__module.model.model.decoder.layers.2.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="352">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="438" name="Constant_46581" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="439" name="__module.model.model.decoder.layers.2.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="354,key_states.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="440" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="441" name="__module.model.model.decoder.layers.2.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="360">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="442" name="__module.model.model.decoder.layers.2.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.2.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="443" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="92834262" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="444" name="Convert_1168709" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="445" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="93653462" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="446" name="Convert_1168712" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="447" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="448" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="93659862" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="449" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="450" name="Constant_1168717" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="451" name="Reshape_1168718" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="452" name="self.model.model.decoder.layers.2.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="453" name="__module.model.model.decoder.layers.2.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="454" name="Constant_45751" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="93685462" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="455" name="__module.model.model.decoder.layers.2.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="357">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="456" name="Constant_46582" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="457" name="__module.model.model.decoder.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="359,value_states.17">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="458" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="459" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Transpose_2" 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="362">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="460" name="__module.model.model.decoder.layers.2.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.2.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="461" name="__module.model.model.decoder.layers.2.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="FP32" names="373,attn_output.17">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="462" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="463" name="__module.model.model.decoder.layers.2.self_attn/aten::transpose/Transpose_3" 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="374,attn_output.19">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="464" name="Constant_46583" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="465" name="__module.model.model.decoder.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="376,input.55">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="466" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="93690582" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="467" name="Convert_1181606" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="468" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="94509782" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="469" name="Convert_1181609" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="470" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="471" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="94516182" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="472" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="473" name="Constant_1181614" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="474" name="Reshape_1181615" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="475" name="self.model.model.decoder.layers.2.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="476" name="__module.model.model.decoder.layers.2.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="477" name="Constant_45752" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="94541782" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="478" name="__module.model.model.decoder.layers.2.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="379,381,input.57">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="479" name="__module.model.model.decoder.layers.2/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>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="385,input.59">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="480" name="__module.model.model.decoder.layers.2.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="481" name="__module.model.model.decoder.layers.2.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="482" name="Constant_45753" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="94546902" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="483" name="__module.model.model.decoder.layers.2.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="484" name="Constant_45754" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="94552022" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="485" name="__module.model.model.decoder.layers.2.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="389,hidden_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="486" name="self.model.model.decoder.layers.2.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="94557142" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="487" name="Convert_1185905" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="488" name="self.model.model.decoder.layers.2.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="95376342" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="489" name="Convert_1185908" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="490" name="self.model.model.decoder.layers.2.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="491" name="self.model.model.decoder.layers.2.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="95382742" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="492" name="self.model.model.decoder.layers.2.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="493" name="Constant_1185913" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="494" name="Reshape_1185914" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="495" name="self.model.model.decoder.layers.2.encoder_attn.q_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="496" name="__module.model.model.decoder.layers.2.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="497" name="Constant_45755" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="95408342" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="498" name="__module.model.model.decoder.layers.2.encoder_attn.q_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="396">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="499" name="Constant_46584" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="500" name="__module.model.model.decoder.layers.2.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="398,query_states.21">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="501" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="502" name="__module.model.model.decoder.layers.2.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="399">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="503" name="__module.model.model.decoder.layers.2.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="401,attn_output.21">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="504" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="505" name="__module.model.model.decoder.layers.2.encoder_attn/aten::transpose/Transpose_1" 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="402,attn_output.23">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="506" name="Constant_46585" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="507" name="__module.model.model.decoder.layers.2.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="404,input.61">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="508" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="95413462" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="509" name="Convert_1190204" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="510" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="96232662" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="511" name="Convert_1190207" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="512" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="513" name="self.model.model.decoder.layers.2.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="96239062" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="514" name="self.model.model.decoder.layers.2.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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="515" name="Constant_1190212" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="516" name="Reshape_1190213" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="517" name="self.model.model.decoder.layers.2.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="518" name="__module.model.model.decoder.layers.2.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="519" name="Constant_45756" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="96264662" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="520" name="__module.model.model.decoder.layers.2.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="407,input.63">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="521" name="__module.model.model.decoder.layers.2/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>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="409,input.65">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="522" name="__module.model.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="523" name="__module.model.model.decoder.layers.2.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="524" name="Constant_45757" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="96269782" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="525" name="__module.model.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="526" name="Constant_45758" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="96274902" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="527" name="__module.model.model.decoder.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="413,input.67">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="528" name="self.model.model.decoder.layers.2.fc1.weight" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 128" offset="96280022" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="529" name="Convert_1099925" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="530" name="self.model.model.decoder.layers.2.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 1" offset="99556822" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="531" name="Convert_1099928" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="532" name="self.model.model.decoder.layers.2.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="533" name="self.model.model.decoder.layers.2.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 10, 1" offset="99582422" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="534" name="self.model.model.decoder.layers.2.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="535" name="Constant_1099933" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="75687350" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="536" name="Reshape_1099934" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="537" name="self.model.model.decoder.layers.2.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="538" name="__module.model.model.decoder.layers.2.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="539" name="Constant_45759" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="99684822" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="540" name="__module.model.model.decoder.layers.2.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="416,input.69">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="541" name="__module.model.model.decoder.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="417,input.71">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="542" name="self.model.model.decoder.layers.2.fc2.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 128" offset="99705302" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="543" name="Convert_1104224" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="544" name="self.model.model.decoder.layers.2.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 1" offset="102982102" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="545" name="Convert_1104227" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="546" name="self.model.model.decoder.layers.2.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="547" name="self.model.model.decoder.layers.2.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 40, 1" offset="103007702" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="548" name="self.model.model.decoder.layers.2.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="549" name="Constant_1104232" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="79112646" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="550" name="Reshape_1104233" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="551" name="self.model.model.decoder.layers.2.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="552" name="__module.model.model.decoder.layers.2.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="553" name="Constant_45760" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103110102" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="554" name="__module.model.model.decoder.layers.2.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="421,input.75">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="555" name="__module.model.model.decoder.layers.2/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="423,425,input.77">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="556" name="__module.model.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="557" name="__module.model.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="558" name="Constant_45761" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103115222" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="559" name="__module.model.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="560" name="Constant_45762" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103120342" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="561" name="__module.model.model.decoder.layers.3.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="438,hidden_states.31">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="562" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="103125462" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="563" name="Convert_1194503" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="564" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="103944662" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="565" name="Convert_1194506" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="566" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="567" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="103951062" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="568" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="569" name="Constant_1194511" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="570" name="Reshape_1194512" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="571" name="self.model.model.decoder.layers.3.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="572" name="__module.model.model.decoder.layers.3.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="573" name="Constant_45763" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="103976662" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="574" name="__module.model.model.decoder.layers.3.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="458">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="575" name="Constant_46586" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="576" name="__module.model.model.decoder.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="460,value_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="577" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="578" name="__module.model.model.decoder.layers.3.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="463">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="579" name="__module.model.model.decoder.layers.3.self_attn/aten::cat/Concat" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.3.decoder.value">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="581" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="103981782" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="582" name="Convert_1198802" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="583" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="104800982" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="584" name="Convert_1198805" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="585" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="586" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="104807382" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="587" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="588" name="Constant_1198810" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="589" name="Reshape_1198811" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="590" name="self.model.model.decoder.layers.3.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="591" name="__module.model.model.decoder.layers.3.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="453">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="592" name="Constant_46587" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="593" name="__module.model.model.decoder.layers.3.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="455,key_states.27">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="594" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="595" name="__module.model.model.decoder.layers.3.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="461">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="596" name="__module.model.model.decoder.layers.3.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
			<data axis="-2" />
			<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="present.3.decoder.key">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="604" name="self.model.model.decoder.layers.3.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="104832982" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="605" name="Convert_1203101" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="606" name="self.model.model.decoder.layers.3.self_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="105652182" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="607" name="Convert_1203104" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="608" name="self.model.model.decoder.layers.3.self_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="609" name="self.model.model.decoder.layers.3.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="105658582" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="610" name="self.model.model.decoder.layers.3.self_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="611" name="Constant_1203109" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="612" name="Reshape_1203110" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="613" name="self.model.model.decoder.layers.3.self_attn.q_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="614" name="__module.model.model.decoder.layers.3.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="615" name="Constant_45764" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="105684182" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="616" name="__module.model.model.decoder.layers.3.self_attn.q_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="447">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="617" name="Constant_46588" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="618" name="__module.model.model.decoder.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="449,query_states.25">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="619" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="620" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Transpose_2" 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="450">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="621" name="__module.model.model.decoder.layers.3.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
				<port id="3" precision="FP32">
					<dim>-1</dim>
					<dim>1</dim>
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="4" precision="FP32" names="474,attn_output.25">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="622" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="623" name="__module.model.model.decoder.layers.3.self_attn/aten::transpose/Transpose_3" 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="475,attn_output.27">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="624" name="Constant_46589" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="625" name="__module.model.model.decoder.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="477,input.79">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="626" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="105689302" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="627" name="Convert_1207400" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="628" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="106508502" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="629" name="Convert_1207403" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="630" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="631" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="106514902" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="632" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="633" name="Constant_1207408" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="634" name="Reshape_1207409" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="635" name="self.model.model.decoder.layers.3.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="636" name="__module.model.model.decoder.layers.3.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="637" name="Constant_45765" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="106540502" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="638" name="__module.model.model.decoder.layers.3.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="480,482,input.81">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="639" name="__module.model.model.decoder.layers.3/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>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="486,input.83">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="640" name="__module.model.model.decoder.layers.3.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="641" name="__module.model.model.decoder.layers.3.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="642" name="Constant_45766" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="106545622" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="643" name="__module.model.model.decoder.layers.3.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="644" name="Constant_45767" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="106550742" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="645" name="__module.model.model.decoder.layers.3.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="490,hidden_states.35">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="646" name="self.model.model.decoder.layers.3.encoder_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="106555862" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="647" name="Convert_1211699" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="648" name="self.model.model.decoder.layers.3.encoder_attn.q_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="107375062" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="649" name="Convert_1211702" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="650" name="self.model.model.decoder.layers.3.encoder_attn.q_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="651" name="self.model.model.decoder.layers.3.encoder_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="107381462" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="652" name="self.model.model.decoder.layers.3.encoder_attn.q_proj.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="653" name="Constant_1211707" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="654" name="Reshape_1211708" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="655" name="self.model.model.decoder.layers.3.encoder_attn.q_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="656" name="__module.model.model.decoder.layers.3.encoder_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="657" name="Constant_45768" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="107407062" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="658" name="__module.model.model.decoder.layers.3.encoder_attn.q_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="497">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="659" name="Constant_46590" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="67985478" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="660" name="__module.model.model.decoder.layers.3.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="499,query_states.29">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="661" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="662" name="__module.model.model.decoder.layers.3.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="500">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="663" name="__module.model.model.decoder.layers.3.encoder_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
			<data causal="false" />
			<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>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="502,attn_output.29">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="664" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="67985510" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="665" name="__module.model.model.decoder.layers.3.encoder_attn/aten::transpose/Transpose_1" 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="503,attn_output">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>20</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="666" name="Constant_46591" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="69693086" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="667" name="__module.model.model.decoder.layers.3.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="505,input.85">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="668" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 128" offset="107412182" size="819200" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="669" name="Convert_1215998" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="670" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 10, 1" offset="108231382" size="6400" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="671" name="Convert_1216001" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="672" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="673" name="self.model.model.decoder.layers.3.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 10, 1" offset="108237782" size="25600" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="674" name="self.model.model.decoder.layers.3.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>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="675" name="Constant_1216006" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="67980342" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="676" name="Reshape_1216007" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="677" name="self.model.model.decoder.layers.3.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="678" name="__module.model.model.decoder.layers.3.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="679" name="Constant_45769" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="108263382" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="680" name="__module.model.model.decoder.layers.3.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="508,input.87">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="681" name="__module.model.model.decoder.layers.3/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>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="510,input.89">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="682" name="__module.model.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="683" name="__module.model.model.decoder.layers.3.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="684" name="Constant_45770" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="108268502" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="685" name="__module.model.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="686" name="Constant_45771" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="108273622" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="687" name="__module.model.model.decoder.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="514,input.91">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="688" name="self.model.model.decoder.layers.3.fc1.weight" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 128" offset="108278742" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="689" name="Convert_1108523" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="690" name="self.model.model.decoder.layers.3.fc1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="5120, 10, 1" offset="111555542" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="691" name="Convert_1108526" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="692" name="self.model.model.decoder.layers.3.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="693" name="self.model.model.decoder.layers.3.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="5120, 10, 1" offset="111581142" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="694" name="self.model.model.decoder.layers.3.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="695" name="Constant_1108531" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="75687350" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="696" name="Reshape_1108532" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>5120</dim>
					<dim>10</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>5120</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="697" name="self.model.model.decoder.layers.3.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="698" name="__module.model.model.decoder.layers.3.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="699" name="Constant_45772" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 5120" offset="111683542" size="20480" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="700" name="__module.model.model.decoder.layers.3.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="517,input.93">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="701" name="__module.model.model.decoder.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="518,input.95">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="702" name="self.model.model.decoder.layers.3.fc2.weight" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 128" offset="111704022" size="3276800" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="703" name="Convert_1112822" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="704" name="self.model.model.decoder.layers.3.fc2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u4" shape="1280, 40, 1" offset="114980822" size="25600" />
			<output>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="705" name="Convert_1112825" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U4">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="706" name="self.model.model.decoder.layers.3.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="707" name="self.model.model.decoder.layers.3.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1280, 40, 1" offset="115006422" size="102400" />
			<output>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="708" name="self.model.model.decoder.layers.3.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="709" name="Constant_1112830" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="79112646" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="710" name="Reshape_1112831" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1280</dim>
					<dim>40</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1280</dim>
					<dim>5120</dim>
				</port>
			</output>
		</layer>
		<layer id="711" name="self.model.model.decoder.layers.3.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="712" name="__module.model.model.decoder.layers.3.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-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="713" name="Constant_45773" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="115108822" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="714" name="__module.model.model.decoder.layers.3.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="522,input.99">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="715" name="__module.model.model.decoder.layers.3/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="524,526,input.101">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="716" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="67118898" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="717" 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="718" name="Constant_45774" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="115113942" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="719" 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="720" name="Constant_45775" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1280" offset="115119062" size="5120" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="721" 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="532,534,544,input">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>1280</dim>
				</port>
			</output>
		</layer>
		<layer id="722" 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="723" name="Result_38660" type="Result" version="opset1" output_names="logits">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>51866</dim>
				</port>
			</input>
		</layer>
		<layer id="603" name="Result_38666" type="Result" version="opset1" output_names="present.0.decoder.key">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="602" name="Result_38665" type="Result" version="opset1" output_names="present.0.decoder.value">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="601" name="Result_38668" type="Result" version="opset1" output_names="present.1.decoder.key">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="600" name="Result_38667" type="Result" version="opset1" output_names="present.1.decoder.value">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="599" name="Result_38670" type="Result" version="opset1" output_names="present.2.decoder.key">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="598" name="Result_38669" type="Result" version="opset1" output_names="present.2.decoder.value">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="597" name="Result_38672" type="Result" version="opset1" output_names="present.3.decoder.key">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
		<layer id="580" name="Result_38671" type="Result" version="opset1" output_names="present.3.decoder.value">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>20</dim>
					<dim>-1</dim>
					<dim>64</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="41" to-port="0" />
		<edge from-layer="0" from-port="0" to-layer="126" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="663" to-port="2" />
		<edge from-layer="2" from-port="0" to-layer="663" to-port="1" />
		<edge from-layer="3" from-port="0" to-layer="579" to-port="0" />
		<edge from-layer="4" from-port="0" to-layer="596" to-port="0" />
		<edge from-layer="5" from-port="0" to-layer="503" to-port="2" />
		<edge from-layer="6" from-port="0" to-layer="503" to-port="1" />
		<edge from-layer="7" from-port="0" to-layer="460" to-port="0" />
		<edge from-layer="8" from-port="0" to-layer="442" to-port="0" />
		<edge from-layer="9" from-port="0" to-layer="351" to-port="2" />
		<edge from-layer="10" from-port="0" to-layer="351" to-port="1" />
		<edge from-layer="11" from-port="0" to-layer="308" to-port="0" />
		<edge from-layer="12" from-port="0" to-layer="290" to-port="0" />
		<edge from-layer="13" from-port="0" to-layer="199" to-port="2" />
		<edge from-layer="14" from-port="0" to-layer="199" to-port="1" />
		<edge from-layer="15" from-port="0" to-layer="109" to-port="0" />
		<edge from-layer="16" from-port="0" to-layer="112" to-port="0" />
		<edge from-layer="16" from-port="0" to-layer="91" to-port="0" />
		<edge from-layer="18" from-port="0" to-layer="28" to-port="0" />
		<edge from-layer="18" from-port="0" to-layer="42" to-port="0" />
		<edge from-layer="19" from-port="0" to-layer="20" to-port="0" />
		<edge from-layer="20" from-port="1" to-layer="23" to-port="0" />
		<edge from-layer="21" from-port="0" to-layer="22" to-port="0" />
		<edge from-layer="22" from-port="1" to-layer="23" to-port="1" />
		<edge from-layer="23" from-port="2" to-layer="25" to-port="0" />
		<edge from-layer="24" from-port="0" to-layer="25" to-port="1" />
		<edge from-layer="25" from-port="2" to-layer="26" to-port="0" />
		<edge from-layer="26" from-port="1" to-layer="722" to-port="1" />
		<edge from-layer="26" from-port="1" to-layer="31" to-port="0" />
		<edge from-layer="27" from-port="0" to-layer="28" to-port="1" />
		<edge from-layer="28" from-port="2" to-layer="29" to-port="0" />
		<edge from-layer="29" from-port="1" to-layer="31" to-port="1" />
		<edge from-layer="30" from-port="0" to-layer="31" to-port="2" />
		<edge from-layer="31" from-port="3" to-layer="52" to-port="0" />
		<edge from-layer="32" from-port="0" to-layer="33" to-port="0" />
		<edge from-layer="33" from-port="1" to-layer="36" to-port="0" />
		<edge from-layer="34" from-port="0" to-layer="35" to-port="0" />
		<edge from-layer="35" from-port="1" to-layer="36" to-port="1" />
		<edge from-layer="36" from-port="2" 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="51" to-port="0" />
		<edge from-layer="40" from-port="0" to-layer="138" to-port="1" />
		<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
		<edge from-layer="41" from-port="2" to-layer="48" to-port="0" />
		<edge from-layer="42" from-port="1" to-layer="118" to-port="0" />
		<edge from-layer="42" from-port="1" to-layer="45" to-port="0" />
		<edge from-layer="43" from-port="0" to-layer="45" to-port="1" />
		<edge from-layer="44" from-port="0" to-layer="45" to-port="2" />
		<edge from-layer="45" from-port="3" to-layer="47" to-port="0" />
		<edge from-layer="45" from-port="3" to-layer="144" to-port="0" />
		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
		<edge from-layer="47" from-port="2" to-layer="48" to-port="1" />
		<edge from-layer="48" from-port="2" to-layer="49" to-port="0" />
		<edge from-layer="49" from-port="1" to-layer="51" to-port="1" />
		<edge from-layer="50" from-port="0" to-layer="51" to-port="2" />
		<edge from-layer="51" from-port="3" to-layer="52" to-port="1" />
		<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
		<edge from-layer="52" from-port="2" to-layer="175" 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="58" to-port="0" />
		<edge from-layer="57" from-port="0" to-layer="58" to-port="1" />
		<edge from-layer="58" from-port="2" to-layer="149" to-port="0" />
		<edge from-layer="58" from-port="2" to-layer="69" to-port="0" />
		<edge from-layer="58" from-port="2" to-layer="102" to-port="0" />
		<edge from-layer="58" from-port="2" to-layer="86" to-port="0" />
		<edge from-layer="59" from-port="0" to-layer="60" to-port="0" />
		<edge from-layer="60" from-port="1" to-layer="63" to-port="0" />
		<edge from-layer="61" from-port="0" to-layer="62" to-port="0" />
		<edge from-layer="62" from-port="1" to-layer="63" to-port="1" />
		<edge from-layer="63" from-port="2" to-layer="65" to-port="0" />
		<edge from-layer="64" from-port="0" to-layer="65" to-port="1" />
		<edge from-layer="65" from-port="2" to-layer="67" to-port="0" />
		<edge from-layer="66" from-port="0" to-layer="67" to-port="1" />
		<edge from-layer="67" from-port="2" to-layer="68" to-port="0" />
		<edge from-layer="68" from-port="1" to-layer="69" to-port="1" />
		<edge from-layer="69" from-port="2" to-layer="71" to-port="0" />
		<edge from-layer="70" from-port="0" to-layer="71" to-port="1" />
		<edge from-layer="71" from-port="2" to-layer="73" to-port="0" />
		<edge from-layer="72" from-port="0" to-layer="73" to-port="1" />
		<edge from-layer="73" from-port="2" to-layer="75" to-port="0" />
		<edge from-layer="74" from-port="0" to-layer="75" to-port="1" />
		<edge from-layer="75" from-port="2" to-layer="157" to-port="0" />
		<edge from-layer="76" from-port="0" to-layer="77" to-port="0" />
		<edge from-layer="77" from-port="1" to-layer="80" to-port="0" />
		<edge from-layer="78" from-port="0" to-layer="79" to-port="0" />
		<edge from-layer="79" from-port="1" 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="1" />
		<edge from-layer="82" from-port="2" to-layer="84" to-port="0" />
		<edge from-layer="83" from-port="0" to-layer="84" to-port="1" />
		<edge from-layer="84" from-port="2" to-layer="85" to-port="0" />
		<edge from-layer="85" from-port="1" to-layer="86" to-port="1" />
		<edge from-layer="86" from-port="2" to-layer="88" to-port="0" />
		<edge from-layer="87" from-port="0" to-layer="88" to-port="1" />
		<edge from-layer="88" from-port="2" to-layer="90" to-port="0" />
		<edge from-layer="89" from-port="0" to-layer="90" to-port="1" />
		<edge from-layer="90" from-port="2" to-layer="91" to-port="1" />
		<edge from-layer="91" from-port="2" to-layer="157" to-port="1" />
		<edge from-layer="91" from-port="2" to-layer="603" to-port="0" />
		<edge from-layer="92" from-port="0" to-layer="93" to-port="0" />
		<edge from-layer="93" from-port="1" to-layer="96" to-port="0" />
		<edge from-layer="94" from-port="0" to-layer="95" to-port="0" />
		<edge from-layer="95" from-port="1" to-layer="96" to-port="1" />
		<edge from-layer="96" from-port="2" to-layer="98" to-port="0" />
		<edge from-layer="97" from-port="0" to-layer="98" to-port="1" />
		<edge from-layer="98" from-port="2" to-layer="100" to-port="0" />
		<edge from-layer="99" from-port="0" to-layer="100" to-port="1" />
		<edge from-layer="100" from-port="2" to-layer="101" to-port="0" />
		<edge from-layer="101" from-port="1" to-layer="102" to-port="1" />
		<edge from-layer="102" from-port="2" to-layer="104" to-port="0" />
		<edge from-layer="103" from-port="0" to-layer="104" to-port="1" />
		<edge from-layer="104" from-port="2" to-layer="106" to-port="0" />
		<edge from-layer="105" from-port="0" to-layer="106" to-port="1" />
		<edge from-layer="106" from-port="2" to-layer="108" to-port="0" />
		<edge from-layer="107" from-port="0" to-layer="108" to-port="1" />
		<edge from-layer="108" from-port="2" to-layer="109" to-port="1" />
		<edge from-layer="109" from-port="2" to-layer="157" to-port="2" />
		<edge from-layer="109" from-port="2" to-layer="602" to-port="0" />
		<edge from-layer="110" from-port="0" to-layer="129" to-port="0" />
		<edge from-layer="111" from-port="0" to-layer="123" to-port="0" />
		<edge from-layer="112" from-port="1" to-layer="115" to-port="0" />
		<edge from-layer="113" from-port="0" to-layer="115" to-port="1" />
		<edge from-layer="114" from-port="0" to-layer="115" to-port="2" />
		<edge from-layer="115" from-port="3" to-layer="119" to-port="0" />
		<edge from-layer="115" from-port="3" to-layer="148" to-port="0" />
		<edge from-layer="116" from-port="0" to-layer="118" to-port="1" />
		<edge from-layer="117" from-port="0" to-layer="118" to-port="2" />
		<edge from-layer="118" from-port="3" to-layer="119" to-port="1" />
		<edge from-layer="118" from-port="3" to-layer="132" to-port="0" />
		<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="1" />
		<edge from-layer="121" from-port="2" to-layer="134" to-port="0" />
		<edge from-layer="122" from-port="0" to-layer="123" to-port="2" />
		<edge from-layer="123" from-port="3" to-layer="124" to-port="0" />
		<edge from-layer="124" from-port="1" to-layer="127" to-port="0" />
		<edge from-layer="125" from-port="0" to-layer="126" to-port="1" />
		<edge from-layer="126" from-port="2" to-layer="127" to-port="1" />
		<edge from-layer="127" from-port="2" to-layer="128" to-port="0" />
		<edge from-layer="128" from-port="1" to-layer="129" to-port="1" />
		<edge from-layer="129" from-port="2" to-layer="137" to-port="0" />
		<edge from-layer="129" from-port="2" to-layer="130" to-port="0" />
		<edge from-layer="130" from-port="1" to-layer="136" to-port="0" />
		<edge from-layer="131" from-port="0" to-layer="132" to-port="1" />
		<edge from-layer="132" from-port="2" to-layer="135" to-port="0" />
		<edge from-layer="133" from-port="0" to-layer="134" to-port="1" />
		<edge from-layer="134" from-port="2" to-layer="135" to-port="1" />
		<edge from-layer="135" from-port="2" to-layer="136" to-port="1" />
		<edge from-layer="136" from-port="2" to-layer="137" to-port="1" />
		<edge from-layer="137" from-port="2" to-layer="138" to-port="0" />
		<edge from-layer="138" from-port="2" to-layer="140" to-port="0" />
		<edge from-layer="139" from-port="0" to-layer="140" to-port="1" />
		<edge from-layer="140" from-port="2" to-layer="145" to-port="0" />
		<edge from-layer="141" from-port="0" to-layer="144" to-port="1" />
		<edge from-layer="142" from-port="0" to-layer="144" to-port="2" />
		<edge from-layer="143" from-port="0" to-layer="144" to-port="3" />
		<edge from-layer="144" from-port="4" to-layer="145" to-port="1" />
		<edge from-layer="145" from-port="2" to-layer="156" to-port="0" />
		<edge from-layer="146" from-port="0" to-layer="156" to-port="1" />
		<edge from-layer="147" from-port="0" to-layer="148" to-port="1" />
		<edge from-layer="148" from-port="2" to-layer="153" to-port="0" />
		<edge from-layer="149" from-port="1" to-layer="152" to-port="0" />
		<edge from-layer="150" from-port="0" to-layer="152" to-port="1" />
		<edge from-layer="151" from-port="0" to-layer="152" to-port="2" />
		<edge from-layer="152" from-port="3" to-layer="153" to-port="1" />
		<edge from-layer="153" from-port="2" to-layer="156" to-port="2" />
		<edge from-layer="154" from-port="0" to-layer="156" to-port="3" />
		<edge from-layer="155" from-port="0" to-layer="156" to-port="4" />
		<edge from-layer="156" from-port="5" to-layer="309" to-port="3" />
		<edge from-layer="156" from-port="5" to-layer="157" to-port="3" />
		<edge from-layer="156" from-port="5" to-layer="621" to-port="3" />
		<edge from-layer="156" from-port="5" to-layer="461" to-port="3" />
		<edge from-layer="157" from-port="4" to-layer="159" to-port="0" />
		<edge from-layer="158" from-port="0" to-layer="159" to-port="1" />
		<edge from-layer="159" from-port="2" to-layer="161" to-port="0" />
		<edge from-layer="160" from-port="0" to-layer="161" to-port="1" />
		<edge from-layer="161" from-port="2" to-layer="172" to-port="0" />
		<edge from-layer="162" from-port="0" to-layer="163" to-port="0" />
		<edge from-layer="163" from-port="1" to-layer="166" to-port="0" />
		<edge from-layer="164" from-port="0" to-layer="165" to-port="0" />
		<edge from-layer="165" from-port="1" to-layer="166" to-port="1" />
		<edge from-layer="166" from-port="2" to-layer="168" to-port="0" />
		<edge from-layer="167" from-port="0" to-layer="168" 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="0" />
		<edge from-layer="171" from-port="1" to-layer="172" to-port="1" />
		<edge from-layer="172" from-port="2" to-layer="174" to-port="0" />
		<edge from-layer="173" from-port="0" to-layer="174" to-port="1" />
		<edge from-layer="174" from-port="2" to-layer="175" to-port="1" />
		<edge from-layer="175" from-port="2" to-layer="217" to-port="0" />
		<edge from-layer="175" from-port="2" to-layer="177" to-port="0" />
		<edge from-layer="176" from-port="0" to-layer="177" to-port="1" />
		<edge from-layer="177" from-port="2" to-layer="179" to-port="0" />
		<edge from-layer="178" from-port="0" to-layer="179" to-port="1" />
		<edge from-layer="179" from-port="2" to-layer="181" to-port="0" />
		<edge from-layer="180" from-port="0" to-layer="181" to-port="1" />
		<edge from-layer="181" from-port="2" to-layer="192" to-port="0" />
		<edge from-layer="182" from-port="0" to-layer="183" to-port="0" />
		<edge from-layer="183" from-port="1" to-layer="186" to-port="0" />
		<edge from-layer="184" from-port="0" to-layer="185" to-port="0" />
		<edge from-layer="185" from-port="1" to-layer="186" to-port="1" />
		<edge from-layer="186" from-port="2" to-layer="188" to-port="0" />
		<edge from-layer="187" from-port="0" to-layer="188" to-port="1" />
		<edge from-layer="188" from-port="2" to-layer="190" to-port="0" />
		<edge from-layer="189" from-port="0" to-layer="190" to-port="1" />
		<edge from-layer="190" from-port="2" to-layer="191" to-port="0" />
		<edge from-layer="191" from-port="1" to-layer="192" to-port="1" />
		<edge from-layer="192" from-port="2" to-layer="194" to-port="0" />
		<edge from-layer="193" from-port="0" to-layer="194" to-port="1" />
		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
		<edge from-layer="195" from-port="0" to-layer="196" to-port="1" />
		<edge from-layer="196" from-port="2" to-layer="198" to-port="0" />
		<edge from-layer="197" from-port="0" to-layer="198" to-port="1" />
		<edge from-layer="198" from-port="2" to-layer="199" to-port="0" />
		<edge from-layer="199" from-port="3" 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="214" 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="208" to-port="0" />
		<edge from-layer="206" from-port="0" to-layer="207" to-port="0" />
		<edge from-layer="207" from-port="1" to-layer="208" to-port="1" />
		<edge from-layer="208" from-port="2" to-layer="210" to-port="0" />
		<edge from-layer="209" from-port="0" to-layer="210" to-port="1" />
		<edge from-layer="210" from-port="2" to-layer="212" to-port="0" />
		<edge from-layer="211" from-port="0" to-layer="212" to-port="1" />
		<edge from-layer="212" from-port="2" to-layer="213" to-port="0" />
		<edge from-layer="213" from-port="1" to-layer="214" to-port="1" />
		<edge from-layer="214" from-port="2" 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="1" />
		<edge from-layer="217" from-port="2" to-layer="251" to-port="0" />
		<edge from-layer="217" from-port="2" to-layer="219" to-port="0" />
		<edge from-layer="218" from-port="0" to-layer="219" to-port="1" />
		<edge from-layer="219" from-port="2" to-layer="221" to-port="0" />
		<edge from-layer="220" from-port="0" to-layer="221" to-port="1" />
		<edge from-layer="221" from-port="2" to-layer="223" to-port="0" />
		<edge from-layer="222" from-port="0" to-layer="223" to-port="1" />
		<edge from-layer="223" from-port="2" to-layer="234" to-port="0" />
		<edge from-layer="224" from-port="0" to-layer="225" to-port="0" />
		<edge from-layer="225" from-port="1" to-layer="228" to-port="0" />
		<edge from-layer="226" from-port="0" to-layer="227" to-port="0" />
		<edge from-layer="227" from-port="1" to-layer="228" to-port="1" />
		<edge from-layer="228" from-port="2" to-layer="230" to-port="0" />
		<edge from-layer="229" from-port="0" to-layer="230" to-port="1" />
		<edge from-layer="230" from-port="2" to-layer="232" to-port="0" />
		<edge from-layer="231" from-port="0" to-layer="232" to-port="1" />
		<edge from-layer="232" from-port="2" to-layer="233" to-port="0" />
		<edge from-layer="233" from-port="1" to-layer="234" to-port="1" />
		<edge from-layer="234" from-port="2" to-layer="236" to-port="0" />
		<edge from-layer="235" from-port="0" to-layer="236" to-port="1" />
		<edge from-layer="236" from-port="2" to-layer="237" to-port="0" />
		<edge from-layer="237" from-port="1" to-layer="248" to-port="0" />
		<edge from-layer="238" from-port="0" to-layer="239" to-port="0" />
		<edge from-layer="239" from-port="1" to-layer="242" 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="242" to-port="1" />
		<edge from-layer="242" from-port="2" to-layer="244" to-port="0" />
		<edge from-layer="243" from-port="0" to-layer="244" to-port="1" />
		<edge from-layer="244" from-port="2" to-layer="246" to-port="0" />
		<edge from-layer="245" from-port="0" to-layer="246" to-port="1" />
		<edge from-layer="246" from-port="2" to-layer="247" to-port="0" />
		<edge from-layer="247" from-port="1" to-layer="248" to-port="1" />
		<edge from-layer="248" from-port="2" to-layer="250" to-port="0" />
		<edge from-layer="249" from-port="0" to-layer="250" to-port="1" />
		<edge from-layer="250" from-port="2" to-layer="251" to-port="1" />
		<edge from-layer="251" from-port="2" to-layer="327" to-port="0" />
		<edge from-layer="251" from-port="2" to-layer="253" to-port="0" />
		<edge from-layer="252" from-port="0" to-layer="253" to-port="1" />
		<edge from-layer="253" from-port="2" to-layer="255" to-port="0" />
		<edge from-layer="254" from-port="0" to-layer="255" to-port="1" />
		<edge from-layer="255" from-port="2" to-layer="257" to-port="0" />
		<edge from-layer="256" from-port="0" to-layer="257" to-port="1" />
		<edge from-layer="257" from-port="2" to-layer="301" to-port="0" />
		<edge from-layer="257" from-port="2" to-layer="268" to-port="0" />
		<edge from-layer="257" from-port="2" to-layer="285" to-port="0" />
		<edge from-layer="258" from-port="0" to-layer="259" to-port="0" />
		<edge from-layer="259" from-port="1" to-layer="262" to-port="0" />
		<edge from-layer="260" from-port="0" to-layer="261" to-port="0" />
		<edge from-layer="261" from-port="1" to-layer="262" to-port="1" />
		<edge from-layer="262" from-port="2" to-layer="264" to-port="0" />
		<edge from-layer="263" from-port="0" to-layer="264" to-port="1" />
		<edge from-layer="264" from-port="2" to-layer="266" to-port="0" />
		<edge from-layer="265" from-port="0" to-layer="266" to-port="1" />
		<edge from-layer="266" from-port="2" to-layer="267" to-port="0" />
		<edge from-layer="267" from-port="1" to-layer="268" to-port="1" />
		<edge from-layer="268" from-port="2" to-layer="270" to-port="0" />
		<edge from-layer="269" from-port="0" to-layer="270" to-port="1" />
		<edge from-layer="270" from-port="2" to-layer="272" to-port="0" />
		<edge from-layer="271" from-port="0" to-layer="272" to-port="1" />
		<edge from-layer="272" from-port="2" to-layer="274" to-port="0" />
		<edge from-layer="273" from-port="0" to-layer="274" to-port="1" />
		<edge from-layer="274" from-port="2" to-layer="309" to-port="0" />
		<edge from-layer="275" from-port="0" to-layer="276" to-port="0" />
		<edge from-layer="276" from-port="1" to-layer="279" to-port="0" />
		<edge from-layer="277" from-port="0" to-layer="278" to-port="0" />
		<edge from-layer="278" from-port="1" to-layer="279" to-port="1" />
		<edge from-layer="279" from-port="2" to-layer="281" to-port="0" />
		<edge from-layer="280" from-port="0" to-layer="281" to-port="1" />
		<edge from-layer="281" from-port="2" to-layer="283" to-port="0" />
		<edge from-layer="282" from-port="0" to-layer="283" to-port="1" />
		<edge from-layer="283" from-port="2" to-layer="284" to-port="0" />
		<edge from-layer="284" from-port="1" to-layer="285" to-port="1" />
		<edge from-layer="285" from-port="2" to-layer="287" to-port="0" />
		<edge from-layer="286" from-port="0" to-layer="287" to-port="1" />
		<edge from-layer="287" from-port="2" to-layer="289" to-port="0" />
		<edge from-layer="288" from-port="0" to-layer="289" to-port="1" />
		<edge from-layer="289" from-port="2" to-layer="290" to-port="1" />
		<edge from-layer="290" from-port="2" to-layer="601" to-port="0" />
		<edge from-layer="290" from-port="2" to-layer="309" to-port="1" />
		<edge from-layer="291" from-port="0" to-layer="292" to-port="0" />
		<edge from-layer="292" from-port="1" to-layer="295" to-port="0" />
		<edge from-layer="293" from-port="0" to-layer="294" to-port="0" />
		<edge from-layer="294" from-port="1" to-layer="295" to-port="1" />
		<edge from-layer="295" from-port="2" to-layer="297" to-port="0" />
		<edge from-layer="296" from-port="0" to-layer="297" to-port="1" />
		<edge from-layer="297" from-port="2" to-layer="299" to-port="0" />
		<edge from-layer="298" from-port="0" to-layer="299" to-port="1" />
		<edge from-layer="299" from-port="2" to-layer="300" to-port="0" />
		<edge from-layer="300" from-port="1" to-layer="301" to-port="1" />
		<edge from-layer="301" from-port="2" to-layer="303" to-port="0" />
		<edge from-layer="302" from-port="0" to-layer="303" to-port="1" />
		<edge from-layer="303" from-port="2" to-layer="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="307" to-port="0" />
		<edge from-layer="306" from-port="0" to-layer="307" to-port="1" />
		<edge from-layer="307" from-port="2" to-layer="308" to-port="1" />
		<edge from-layer="308" from-port="2" to-layer="309" to-port="2" />
		<edge from-layer="308" from-port="2" to-layer="600" to-port="0" />
		<edge from-layer="309" from-port="4" 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="313" to-port="0" />
		<edge from-layer="312" from-port="0" to-layer="313" to-port="1" />
		<edge from-layer="313" from-port="2" to-layer="324" to-port="0" />
		<edge from-layer="314" from-port="0" to-layer="315" to-port="0" />
		<edge from-layer="315" from-port="1" to-layer="318" to-port="0" />
		<edge from-layer="316" from-port="0" to-layer="317" to-port="0" />
		<edge from-layer="317" from-port="1" to-layer="318" to-port="1" />
		<edge from-layer="318" from-port="2" to-layer="320" to-port="0" />
		<edge from-layer="319" from-port="0" to-layer="320" to-port="1" />
		<edge from-layer="320" from-port="2" to-layer="322" to-port="0" />
		<edge from-layer="321" from-port="0" to-layer="322" to-port="1" />
		<edge from-layer="322" from-port="2" to-layer="323" to-port="0" />
		<edge from-layer="323" from-port="1" to-layer="324" to-port="1" />
		<edge from-layer="324" from-port="2" to-layer="326" to-port="0" />
		<edge from-layer="325" from-port="0" to-layer="326" to-port="1" />
		<edge from-layer="326" from-port="2" to-layer="327" to-port="1" />
		<edge from-layer="327" from-port="2" to-layer="369" to-port="0" />
		<edge from-layer="327" from-port="2" to-layer="329" to-port="0" />
		<edge from-layer="328" from-port="0" 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="333" to-port="0" />
		<edge from-layer="332" from-port="0" to-layer="333" to-port="1" />
		<edge from-layer="333" from-port="2" to-layer="344" to-port="0" />
		<edge from-layer="334" from-port="0" to-layer="335" to-port="0" />
		<edge from-layer="335" from-port="1" to-layer="338" to-port="0" />
		<edge from-layer="336" from-port="0" to-layer="337" to-port="0" />
		<edge from-layer="337" from-port="1" to-layer="338" to-port="1" />
		<edge from-layer="338" from-port="2" to-layer="340" to-port="0" />
		<edge from-layer="339" from-port="0" to-layer="340" to-port="1" />
		<edge from-layer="340" from-port="2" 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="348" to-port="0" />
		<edge from-layer="347" from-port="0" to-layer="348" to-port="1" />
		<edge from-layer="348" from-port="2" to-layer="350" to-port="0" />
		<edge from-layer="349" from-port="0" to-layer="350" to-port="1" />
		<edge from-layer="350" from-port="2" to-layer="351" to-port="0" />
		<edge from-layer="351" from-port="3" to-layer="353" to-port="0" />
		<edge from-layer="352" from-port="0" to-layer="353" to-port="1" />
		<edge from-layer="353" from-port="2" to-layer="355" to-port="0" />
		<edge from-layer="354" from-port="0" to-layer="355" to-port="1" />
		<edge from-layer="355" from-port="2" to-layer="366" to-port="0" />
		<edge from-layer="356" from-port="0" to-layer="357" to-port="0" />
		<edge from-layer="357" from-port="1" to-layer="360" to-port="0" />
		<edge from-layer="358" from-port="0" to-layer="359" to-port="0" />
		<edge from-layer="359" from-port="1" to-layer="360" to-port="1" />
		<edge from-layer="360" from-port="2" to-layer="362" to-port="0" />
		<edge from-layer="361" from-port="0" to-layer="362" to-port="1" />
		<edge from-layer="362" from-port="2" to-layer="364" to-port="0" />
		<edge from-layer="363" from-port="0" to-layer="364" to-port="1" />
		<edge from-layer="364" from-port="2" to-layer="365" to-port="0" />
		<edge from-layer="365" from-port="1" to-layer="366" to-port="1" />
		<edge from-layer="366" from-port="2" to-layer="368" to-port="0" />
		<edge from-layer="367" from-port="0" to-layer="368" to-port="1" />
		<edge from-layer="368" from-port="2" to-layer="369" to-port="1" />
		<edge from-layer="369" from-port="2" to-layer="403" to-port="0" />
		<edge from-layer="369" from-port="2" to-layer="371" to-port="0" />
		<edge from-layer="370" from-port="0" to-layer="371" to-port="1" />
		<edge from-layer="371" from-port="2" to-layer="373" to-port="0" />
		<edge from-layer="372" from-port="0" to-layer="373" to-port="1" />
		<edge from-layer="373" from-port="2" to-layer="375" to-port="0" />
		<edge from-layer="374" from-port="0" to-layer="375" to-port="1" />
		<edge from-layer="375" from-port="2" to-layer="386" to-port="0" />
		<edge from-layer="376" from-port="0" to-layer="377" to-port="0" />
		<edge from-layer="377" from-port="1" to-layer="380" to-port="0" />
		<edge from-layer="378" from-port="0" to-layer="379" to-port="0" />
		<edge from-layer="379" from-port="1" to-layer="380" to-port="1" />
		<edge from-layer="380" from-port="2" to-layer="382" to-port="0" />
		<edge from-layer="381" from-port="0" to-layer="382" to-port="1" />
		<edge from-layer="382" from-port="2" to-layer="384" to-port="0" />
		<edge from-layer="383" from-port="0" to-layer="384" to-port="1" />
		<edge from-layer="384" from-port="2" to-layer="385" to-port="0" />
		<edge from-layer="385" from-port="1" to-layer="386" to-port="1" />
		<edge from-layer="386" from-port="2" to-layer="388" to-port="0" />
		<edge from-layer="387" from-port="0" to-layer="388" to-port="1" />
		<edge from-layer="388" from-port="2" to-layer="389" to-port="0" />
		<edge from-layer="389" from-port="1" to-layer="400" to-port="0" />
		<edge from-layer="390" from-port="0" to-layer="391" to-port="0" />
		<edge from-layer="391" from-port="1" to-layer="394" to-port="0" />
		<edge from-layer="392" from-port="0" to-layer="393" to-port="0" />
		<edge from-layer="393" from-port="1" to-layer="394" to-port="1" />
		<edge from-layer="394" from-port="2" to-layer="396" to-port="0" />
		<edge from-layer="395" from-port="0" to-layer="396" to-port="1" />
		<edge from-layer="396" from-port="2" to-layer="398" to-port="0" />
		<edge from-layer="397" from-port="0" to-layer="398" to-port="1" />
		<edge from-layer="398" from-port="2" to-layer="399" to-port="0" />
		<edge from-layer="399" from-port="1" to-layer="400" to-port="1" />
		<edge from-layer="400" from-port="2" to-layer="402" to-port="0" />
		<edge from-layer="401" from-port="0" to-layer="402" to-port="1" />
		<edge from-layer="402" from-port="2" to-layer="403" to-port="1" />
		<edge from-layer="403" from-port="2" to-layer="405" to-port="0" />
		<edge from-layer="403" from-port="2" to-layer="479" to-port="0" />
		<edge from-layer="404" from-port="0" to-layer="405" to-port="1" />
		<edge from-layer="405" from-port="2" to-layer="407" to-port="0" />
		<edge from-layer="406" from-port="0" to-layer="407" to-port="1" />
		<edge from-layer="407" from-port="2" to-layer="409" to-port="0" />
		<edge from-layer="408" from-port="0" to-layer="409" to-port="1" />
		<edge from-layer="409" from-port="2" to-layer="453" to-port="0" />
		<edge from-layer="409" from-port="2" to-layer="420" to-port="0" />
		<edge from-layer="409" from-port="2" to-layer="437" to-port="0" />
		<edge from-layer="410" from-port="0" to-layer="411" to-port="0" />
		<edge from-layer="411" from-port="1" to-layer="414" to-port="0" />
		<edge from-layer="412" from-port="0" to-layer="413" to-port="0" />
		<edge from-layer="413" from-port="1" to-layer="414" to-port="1" />
		<edge from-layer="414" from-port="2" to-layer="416" to-port="0" />
		<edge from-layer="415" from-port="0" to-layer="416" to-port="1" />
		<edge from-layer="416" from-port="2" to-layer="418" to-port="0" />
		<edge from-layer="417" from-port="0" to-layer="418" to-port="1" />
		<edge from-layer="418" from-port="2" to-layer="419" to-port="0" />
		<edge from-layer="419" from-port="1" to-layer="420" to-port="1" />
		<edge from-layer="420" from-port="2" to-layer="422" to-port="0" />
		<edge from-layer="421" from-port="0" to-layer="422" to-port="1" />
		<edge from-layer="422" from-port="2" to-layer="424" to-port="0" />
		<edge from-layer="423" from-port="0" to-layer="424" to-port="1" />
		<edge from-layer="424" from-port="2" to-layer="426" to-port="0" />
		<edge from-layer="425" from-port="0" to-layer="426" to-port="1" />
		<edge from-layer="426" from-port="2" to-layer="461" to-port="0" />
		<edge from-layer="427" from-port="0" to-layer="428" to-port="0" />
		<edge from-layer="428" from-port="1" to-layer="431" to-port="0" />
		<edge from-layer="429" from-port="0" to-layer="430" to-port="0" />
		<edge from-layer="430" from-port="1" to-layer="431" to-port="1" />
		<edge from-layer="431" from-port="2" to-layer="433" to-port="0" />
		<edge from-layer="432" from-port="0" to-layer="433" to-port="1" />
		<edge from-layer="433" from-port="2" to-layer="435" to-port="0" />
		<edge from-layer="434" from-port="0" to-layer="435" to-port="1" />
		<edge from-layer="435" from-port="2" to-layer="436" to-port="0" />
		<edge from-layer="436" from-port="1" to-layer="437" to-port="1" />
		<edge from-layer="437" from-port="2" to-layer="439" to-port="0" />
		<edge from-layer="438" from-port="0" to-layer="439" to-port="1" />
		<edge from-layer="439" from-port="2" to-layer="441" to-port="0" />
		<edge from-layer="440" from-port="0" to-layer="441" to-port="1" />
		<edge from-layer="441" from-port="2" to-layer="442" to-port="1" />
		<edge from-layer="442" from-port="2" to-layer="599" to-port="0" />
		<edge from-layer="442" from-port="2" to-layer="461" to-port="1" />
		<edge from-layer="443" from-port="0" to-layer="444" to-port="0" />
		<edge from-layer="444" from-port="1" to-layer="447" to-port="0" />
		<edge from-layer="445" from-port="0" to-layer="446" to-port="0" />
		<edge from-layer="446" from-port="1" to-layer="447" to-port="1" />
		<edge from-layer="447" from-port="2" to-layer="449" to-port="0" />
		<edge from-layer="448" from-port="0" to-layer="449" to-port="1" />
		<edge from-layer="449" from-port="2" to-layer="451" to-port="0" />
		<edge from-layer="450" from-port="0" to-layer="451" to-port="1" />
		<edge from-layer="451" from-port="2" to-layer="452" to-port="0" />
		<edge from-layer="452" from-port="1" to-layer="453" to-port="1" />
		<edge from-layer="453" from-port="2" to-layer="455" to-port="0" />
		<edge from-layer="454" from-port="0" to-layer="455" to-port="1" />
		<edge from-layer="455" from-port="2" to-layer="457" to-port="0" />
		<edge from-layer="456" from-port="0" to-layer="457" to-port="1" />
		<edge from-layer="457" from-port="2" to-layer="459" to-port="0" />
		<edge from-layer="458" from-port="0" to-layer="459" to-port="1" />
		<edge from-layer="459" from-port="2" to-layer="460" to-port="1" />
		<edge from-layer="460" from-port="2" to-layer="598" to-port="0" />
		<edge from-layer="460" from-port="2" to-layer="461" to-port="2" />
		<edge from-layer="461" from-port="4" to-layer="463" to-port="0" />
		<edge from-layer="462" from-port="0" to-layer="463" to-port="1" />
		<edge from-layer="463" from-port="2" to-layer="465" to-port="0" />
		<edge from-layer="464" from-port="0" to-layer="465" to-port="1" />
		<edge from-layer="465" from-port="2" to-layer="476" to-port="0" />
		<edge from-layer="466" from-port="0" to-layer="467" to-port="0" />
		<edge from-layer="467" from-port="1" to-layer="470" to-port="0" />
		<edge from-layer="468" from-port="0" to-layer="469" to-port="0" />
		<edge from-layer="469" from-port="1" to-layer="470" to-port="1" />
		<edge from-layer="470" from-port="2" to-layer="472" to-port="0" />
		<edge from-layer="471" from-port="0" to-layer="472" to-port="1" />
		<edge from-layer="472" from-port="2" to-layer="474" to-port="0" />
		<edge from-layer="473" from-port="0" to-layer="474" to-port="1" />
		<edge from-layer="474" from-port="2" to-layer="475" to-port="0" />
		<edge from-layer="475" from-port="1" to-layer="476" to-port="1" />
		<edge from-layer="476" from-port="2" to-layer="478" to-port="0" />
		<edge from-layer="477" from-port="0" to-layer="478" to-port="1" />
		<edge from-layer="478" from-port="2" to-layer="479" to-port="1" />
		<edge from-layer="479" from-port="2" to-layer="481" to-port="0" />
		<edge from-layer="479" from-port="2" to-layer="521" to-port="0" />
		<edge from-layer="480" from-port="0" to-layer="481" to-port="1" />
		<edge from-layer="481" from-port="2" to-layer="483" to-port="0" />
		<edge from-layer="482" from-port="0" to-layer="483" to-port="1" />
		<edge from-layer="483" from-port="2" to-layer="485" to-port="0" />
		<edge from-layer="484" from-port="0" to-layer="485" to-port="1" />
		<edge from-layer="485" from-port="2" to-layer="496" to-port="0" />
		<edge from-layer="486" from-port="0" to-layer="487" to-port="0" />
		<edge from-layer="487" from-port="1" to-layer="490" to-port="0" />
		<edge from-layer="488" from-port="0" to-layer="489" to-port="0" />
		<edge from-layer="489" from-port="1" to-layer="490" to-port="1" />
		<edge from-layer="490" from-port="2" to-layer="492" to-port="0" />
		<edge from-layer="491" from-port="0" to-layer="492" to-port="1" />
		<edge from-layer="492" from-port="2" to-layer="494" to-port="0" />
		<edge from-layer="493" from-port="0" to-layer="494" to-port="1" />
		<edge from-layer="494" from-port="2" to-layer="495" to-port="0" />
		<edge from-layer="495" from-port="1" to-layer="496" to-port="1" />
		<edge from-layer="496" from-port="2" to-layer="498" to-port="0" />
		<edge from-layer="497" from-port="0" to-layer="498" to-port="1" />
		<edge from-layer="498" from-port="2" to-layer="500" to-port="0" />
		<edge from-layer="499" from-port="0" to-layer="500" to-port="1" />
		<edge from-layer="500" from-port="2" to-layer="502" to-port="0" />
		<edge from-layer="501" from-port="0" to-layer="502" to-port="1" />
		<edge from-layer="502" from-port="2" to-layer="503" to-port="0" />
		<edge from-layer="503" from-port="3" to-layer="505" to-port="0" />
		<edge from-layer="504" from-port="0" to-layer="505" to-port="1" />
		<edge from-layer="505" from-port="2" to-layer="507" to-port="0" />
		<edge from-layer="506" from-port="0" to-layer="507" to-port="1" />
		<edge from-layer="507" from-port="2" to-layer="518" to-port="0" />
		<edge from-layer="508" from-port="0" to-layer="509" to-port="0" />
		<edge from-layer="509" from-port="1" to-layer="512" to-port="0" />
		<edge from-layer="510" from-port="0" to-layer="511" to-port="0" />
		<edge from-layer="511" from-port="1" to-layer="512" to-port="1" />
		<edge from-layer="512" from-port="2" to-layer="514" to-port="0" />
		<edge from-layer="513" from-port="0" to-layer="514" to-port="1" />
		<edge from-layer="514" from-port="2" to-layer="516" to-port="0" />
		<edge from-layer="515" from-port="0" to-layer="516" to-port="1" />
		<edge from-layer="516" from-port="2" to-layer="517" to-port="0" />
		<edge from-layer="517" from-port="1" to-layer="518" to-port="1" />
		<edge from-layer="518" from-port="2" to-layer="520" to-port="0" />
		<edge from-layer="519" from-port="0" to-layer="520" to-port="1" />
		<edge from-layer="520" from-port="2" to-layer="521" to-port="1" />
		<edge from-layer="521" from-port="2" to-layer="555" to-port="0" />
		<edge from-layer="521" from-port="2" to-layer="523" to-port="0" />
		<edge from-layer="522" from-port="0" to-layer="523" to-port="1" />
		<edge from-layer="523" from-port="2" to-layer="525" to-port="0" />
		<edge from-layer="524" from-port="0" to-layer="525" to-port="1" />
		<edge from-layer="525" from-port="2" to-layer="527" to-port="0" />
		<edge from-layer="526" from-port="0" to-layer="527" to-port="1" />
		<edge from-layer="527" from-port="2" to-layer="538" to-port="0" />
		<edge from-layer="528" from-port="0" to-layer="529" to-port="0" />
		<edge from-layer="529" from-port="1" to-layer="532" to-port="0" />
		<edge from-layer="530" from-port="0" to-layer="531" to-port="0" />
		<edge from-layer="531" from-port="1" to-layer="532" to-port="1" />
		<edge from-layer="532" from-port="2" to-layer="534" to-port="0" />
		<edge from-layer="533" from-port="0" to-layer="534" to-port="1" />
		<edge from-layer="534" from-port="2" to-layer="536" to-port="0" />
		<edge from-layer="535" from-port="0" to-layer="536" to-port="1" />
		<edge from-layer="536" from-port="2" to-layer="537" to-port="0" />
		<edge from-layer="537" from-port="1" to-layer="538" to-port="1" />
		<edge from-layer="538" from-port="2" to-layer="540" to-port="0" />
		<edge from-layer="539" from-port="0" to-layer="540" to-port="1" />
		<edge from-layer="540" from-port="2" to-layer="541" to-port="0" />
		<edge from-layer="541" from-port="1" to-layer="552" to-port="0" />
		<edge from-layer="542" from-port="0" to-layer="543" to-port="0" />
		<edge from-layer="543" from-port="1" to-layer="546" to-port="0" />
		<edge from-layer="544" from-port="0" to-layer="545" to-port="0" />
		<edge from-layer="545" from-port="1" to-layer="546" to-port="1" />
		<edge from-layer="546" from-port="2" to-layer="548" to-port="0" />
		<edge from-layer="547" from-port="0" to-layer="548" to-port="1" />
		<edge from-layer="548" from-port="2" to-layer="550" to-port="0" />
		<edge from-layer="549" from-port="0" to-layer="550" to-port="1" />
		<edge from-layer="550" from-port="2" to-layer="551" to-port="0" />
		<edge from-layer="551" from-port="1" to-layer="552" to-port="1" />
		<edge from-layer="552" from-port="2" to-layer="554" to-port="0" />
		<edge from-layer="553" from-port="0" to-layer="554" to-port="1" />
		<edge from-layer="554" from-port="2" to-layer="555" to-port="1" />
		<edge from-layer="555" from-port="2" to-layer="639" to-port="0" />
		<edge from-layer="555" from-port="2" to-layer="557" to-port="0" />
		<edge from-layer="556" from-port="0" to-layer="557" to-port="1" />
		<edge from-layer="557" from-port="2" to-layer="559" to-port="0" />
		<edge from-layer="558" from-port="0" to-layer="559" to-port="1" />
		<edge from-layer="559" from-port="2" to-layer="561" to-port="0" />
		<edge from-layer="560" from-port="0" to-layer="561" to-port="1" />
		<edge from-layer="561" from-port="2" to-layer="591" to-port="0" />
		<edge from-layer="561" from-port="2" to-layer="614" to-port="0" />
		<edge from-layer="561" from-port="2" to-layer="572" to-port="0" />
		<edge from-layer="562" from-port="0" to-layer="563" to-port="0" />
		<edge from-layer="563" from-port="1" to-layer="566" to-port="0" />
		<edge from-layer="564" from-port="0" to-layer="565" to-port="0" />
		<edge from-layer="565" from-port="1" to-layer="566" to-port="1" />
		<edge from-layer="566" from-port="2" to-layer="568" to-port="0" />
		<edge from-layer="567" from-port="0" to-layer="568" to-port="1" />
		<edge from-layer="568" from-port="2" to-layer="570" to-port="0" />
		<edge from-layer="569" from-port="0" to-layer="570" to-port="1" />
		<edge from-layer="570" from-port="2" to-layer="571" to-port="0" />
		<edge from-layer="571" from-port="1" to-layer="572" to-port="1" />
		<edge from-layer="572" from-port="2" to-layer="574" to-port="0" />
		<edge from-layer="573" from-port="0" to-layer="574" to-port="1" />
		<edge from-layer="574" from-port="2" to-layer="576" to-port="0" />
		<edge from-layer="575" from-port="0" to-layer="576" to-port="1" />
		<edge from-layer="576" from-port="2" to-layer="578" to-port="0" />
		<edge from-layer="577" from-port="0" to-layer="578" to-port="1" />
		<edge from-layer="578" from-port="2" to-layer="579" to-port="1" />
		<edge from-layer="579" from-port="2" to-layer="621" to-port="2" />
		<edge from-layer="579" from-port="2" to-layer="580" to-port="0" />
		<edge from-layer="581" from-port="0" to-layer="582" to-port="0" />
		<edge from-layer="582" from-port="1" to-layer="585" to-port="0" />
		<edge from-layer="583" from-port="0" to-layer="584" to-port="0" />
		<edge from-layer="584" from-port="1" to-layer="585" to-port="1" />
		<edge from-layer="585" from-port="2" to-layer="587" to-port="0" />
		<edge from-layer="586" from-port="0" to-layer="587" to-port="1" />
		<edge from-layer="587" from-port="2" to-layer="589" to-port="0" />
		<edge from-layer="588" from-port="0" to-layer="589" to-port="1" />
		<edge from-layer="589" from-port="2" to-layer="590" to-port="0" />
		<edge from-layer="590" from-port="1" to-layer="591" to-port="1" />
		<edge from-layer="591" from-port="2" to-layer="593" to-port="0" />
		<edge from-layer="592" from-port="0" to-layer="593" to-port="1" />
		<edge from-layer="593" from-port="2" to-layer="595" to-port="0" />
		<edge from-layer="594" from-port="0" to-layer="595" to-port="1" />
		<edge from-layer="595" from-port="2" to-layer="596" to-port="1" />
		<edge from-layer="596" from-port="2" to-layer="597" to-port="0" />
		<edge from-layer="596" from-port="2" to-layer="621" to-port="1" />
		<edge from-layer="604" from-port="0" to-layer="605" to-port="0" />
		<edge from-layer="605" from-port="1" to-layer="608" to-port="0" />
		<edge from-layer="606" from-port="0" to-layer="607" to-port="0" />
		<edge from-layer="607" from-port="1" to-layer="608" to-port="1" />
		<edge from-layer="608" from-port="2" to-layer="610" to-port="0" />
		<edge from-layer="609" from-port="0" to-layer="610" to-port="1" />
		<edge from-layer="610" from-port="2" to-layer="612" to-port="0" />
		<edge from-layer="611" from-port="0" to-layer="612" to-port="1" />
		<edge from-layer="612" from-port="2" to-layer="613" to-port="0" />
		<edge from-layer="613" from-port="1" to-layer="614" to-port="1" />
		<edge from-layer="614" from-port="2" to-layer="616" to-port="0" />
		<edge from-layer="615" from-port="0" to-layer="616" to-port="1" />
		<edge from-layer="616" from-port="2" to-layer="618" to-port="0" />
		<edge from-layer="617" from-port="0" to-layer="618" to-port="1" />
		<edge from-layer="618" from-port="2" to-layer="620" to-port="0" />
		<edge from-layer="619" from-port="0" to-layer="620" to-port="1" />
		<edge from-layer="620" from-port="2" to-layer="621" to-port="0" />
		<edge from-layer="621" from-port="4" to-layer="623" to-port="0" />
		<edge from-layer="622" from-port="0" to-layer="623" to-port="1" />
		<edge from-layer="623" from-port="2" to-layer="625" to-port="0" />
		<edge from-layer="624" from-port="0" to-layer="625" to-port="1" />
		<edge from-layer="625" from-port="2" to-layer="636" to-port="0" />
		<edge from-layer="626" from-port="0" to-layer="627" to-port="0" />
		<edge from-layer="627" from-port="1" to-layer="630" to-port="0" />
		<edge from-layer="628" from-port="0" to-layer="629" to-port="0" />
		<edge from-layer="629" from-port="1" to-layer="630" to-port="1" />
		<edge from-layer="630" from-port="2" to-layer="632" to-port="0" />
		<edge from-layer="631" from-port="0" to-layer="632" to-port="1" />
		<edge from-layer="632" from-port="2" to-layer="634" to-port="0" />
		<edge from-layer="633" from-port="0" to-layer="634" to-port="1" />
		<edge from-layer="634" from-port="2" to-layer="635" to-port="0" />
		<edge from-layer="635" from-port="1" to-layer="636" to-port="1" />
		<edge from-layer="636" from-port="2" to-layer="638" to-port="0" />
		<edge from-layer="637" from-port="0" to-layer="638" to-port="1" />
		<edge from-layer="638" from-port="2" to-layer="639" to-port="1" />
		<edge from-layer="639" from-port="2" to-layer="681" to-port="0" />
		<edge from-layer="639" from-port="2" to-layer="641" to-port="0" />
		<edge from-layer="640" from-port="0" to-layer="641" to-port="1" />
		<edge from-layer="641" from-port="2" to-layer="643" to-port="0" />
		<edge from-layer="642" from-port="0" to-layer="643" to-port="1" />
		<edge from-layer="643" from-port="2" to-layer="645" to-port="0" />
		<edge from-layer="644" from-port="0" to-layer="645" to-port="1" />
		<edge from-layer="645" from-port="2" to-layer="656" to-port="0" />
		<edge from-layer="646" from-port="0" to-layer="647" to-port="0" />
		<edge from-layer="647" from-port="1" to-layer="650" to-port="0" />
		<edge from-layer="648" from-port="0" to-layer="649" to-port="0" />
		<edge from-layer="649" from-port="1" to-layer="650" to-port="1" />
		<edge from-layer="650" from-port="2" to-layer="652" to-port="0" />
		<edge from-layer="651" from-port="0" to-layer="652" to-port="1" />
		<edge from-layer="652" from-port="2" to-layer="654" to-port="0" />
		<edge from-layer="653" from-port="0" to-layer="654" to-port="1" />
		<edge from-layer="654" from-port="2" to-layer="655" to-port="0" />
		<edge from-layer="655" from-port="1" to-layer="656" to-port="1" />
		<edge from-layer="656" from-port="2" to-layer="658" to-port="0" />
		<edge from-layer="657" from-port="0" to-layer="658" to-port="1" />
		<edge from-layer="658" from-port="2" to-layer="660" to-port="0" />
		<edge from-layer="659" from-port="0" to-layer="660" to-port="1" />
		<edge from-layer="660" from-port="2" to-layer="662" to-port="0" />
		<edge from-layer="661" from-port="0" to-layer="662" to-port="1" />
		<edge from-layer="662" from-port="2" to-layer="663" to-port="0" />
		<edge from-layer="663" from-port="3" to-layer="665" to-port="0" />
		<edge from-layer="664" from-port="0" to-layer="665" to-port="1" />
		<edge from-layer="665" from-port="2" to-layer="667" to-port="0" />
		<edge from-layer="666" from-port="0" to-layer="667" to-port="1" />
		<edge from-layer="667" from-port="2" to-layer="678" to-port="0" />
		<edge from-layer="668" from-port="0" to-layer="669" to-port="0" />
		<edge from-layer="669" from-port="1" to-layer="672" to-port="0" />
		<edge from-layer="670" from-port="0" to-layer="671" to-port="0" />
		<edge from-layer="671" from-port="1" to-layer="672" to-port="1" />
		<edge from-layer="672" from-port="2" to-layer="674" to-port="0" />
		<edge from-layer="673" from-port="0" to-layer="674" to-port="1" />
		<edge from-layer="674" from-port="2" to-layer="676" to-port="0" />
		<edge from-layer="675" from-port="0" to-layer="676" to-port="1" />
		<edge from-layer="676" from-port="2" to-layer="677" to-port="0" />
		<edge from-layer="677" from-port="1" to-layer="678" to-port="1" />
		<edge from-layer="678" from-port="2" to-layer="680" to-port="0" />
		<edge from-layer="679" from-port="0" to-layer="680" to-port="1" />
		<edge from-layer="680" from-port="2" to-layer="681" to-port="1" />
		<edge from-layer="681" from-port="2" to-layer="683" to-port="0" />
		<edge from-layer="681" from-port="2" to-layer="715" to-port="0" />
		<edge from-layer="682" from-port="0" to-layer="683" to-port="1" />
		<edge from-layer="683" from-port="2" to-layer="685" to-port="0" />
		<edge from-layer="684" from-port="0" to-layer="685" to-port="1" />
		<edge from-layer="685" from-port="2" to-layer="687" to-port="0" />
		<edge from-layer="686" from-port="0" to-layer="687" to-port="1" />
		<edge from-layer="687" from-port="2" to-layer="698" to-port="0" />
		<edge from-layer="688" from-port="0" to-layer="689" to-port="0" />
		<edge from-layer="689" from-port="1" to-layer="692" to-port="0" />
		<edge from-layer="690" from-port="0" to-layer="691" to-port="0" />
		<edge from-layer="691" from-port="1" to-layer="692" to-port="1" />
		<edge from-layer="692" from-port="2" to-layer="694" to-port="0" />
		<edge from-layer="693" from-port="0" to-layer="694" to-port="1" />
		<edge from-layer="694" from-port="2" to-layer="696" to-port="0" />
		<edge from-layer="695" from-port="0" to-layer="696" to-port="1" />
		<edge from-layer="696" from-port="2" to-layer="697" to-port="0" />
		<edge from-layer="697" from-port="1" to-layer="698" to-port="1" />
		<edge from-layer="698" from-port="2" to-layer="700" to-port="0" />
		<edge from-layer="699" from-port="0" to-layer="700" to-port="1" />
		<edge from-layer="700" from-port="2" to-layer="701" to-port="0" />
		<edge from-layer="701" from-port="1" to-layer="712" to-port="0" />
		<edge from-layer="702" from-port="0" to-layer="703" to-port="0" />
		<edge from-layer="703" from-port="1" to-layer="706" to-port="0" />
		<edge from-layer="704" from-port="0" to-layer="705" to-port="0" />
		<edge from-layer="705" from-port="1" to-layer="706" to-port="1" />
		<edge from-layer="706" from-port="2" to-layer="708" to-port="0" />
		<edge from-layer="707" from-port="0" to-layer="708" to-port="1" />
		<edge from-layer="708" from-port="2" to-layer="710" to-port="0" />
		<edge from-layer="709" from-port="0" to-layer="710" to-port="1" />
		<edge from-layer="710" from-port="2" to-layer="711" to-port="0" />
		<edge from-layer="711" from-port="1" to-layer="712" to-port="1" />
		<edge from-layer="712" from-port="2" to-layer="714" to-port="0" />
		<edge from-layer="713" from-port="0" to-layer="714" to-port="1" />
		<edge from-layer="714" from-port="2" to-layer="715" to-port="1" />
		<edge from-layer="715" from-port="2" to-layer="717" to-port="0" />
		<edge from-layer="716" from-port="0" to-layer="717" to-port="1" />
		<edge from-layer="717" from-port="2" to-layer="719" to-port="0" />
		<edge from-layer="718" from-port="0" to-layer="719" to-port="1" />
		<edge from-layer="719" from-port="2" to-layer="721" to-port="0" />
		<edge from-layer="720" from-port="0" to-layer="721" to-port="1" />
		<edge from-layer="721" from-port="2" to-layer="722" to-port="0" />
		<edge from-layer="722" from-port="2" to-layer="723" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<nncf>
			<friendly_names_were_updated value="True" />
			<version value="2.17.0" />
			<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, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'lora_adapter_rank': 256, 'backend_params': {}}" />
				<all_layers value="False" />
				<awq value="False" />
				<backup_mode value="int8_asym" />
				<compression_format value="dequantize" />
				<gptq value="False" />
				<group_size value="128" />
				<ignored_scope value="[]" />
				<lora_correction value="False" />
				<mode value="int4_asym" />
				<ratio value="1.0" />
				<scale_estimation value="False" />
				<sensitivity_metric value="weight_quantization_error" />
			</weight_compression>
		</nncf>
		<optimum>
			<nncf_version value="2.17.0" />
			<optimum_intel_version value="1.24.0" />
			<optimum_version value="1.26.1" />
			<pytorch_version value="2.7.1" />
			<transformers_version value="4.52.4" />
		</optimum>
	</rt_info>
</net>