openvino_encoder_model.xml

<?xml version="1.0"?>
<net name="Model0" version="11">
	<layers>
		<layer id="0" name="input_features" type="Parameter" version="opset1">
			<data shape="?,80,3000" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="input_features">
					<dim>-1</dim>
					<dim>80</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="self.conv1.weight" type="Const" version="opset1">
			<data element_type="u8" shape="384, 80, 3" offset="0" size="92160" />
			<output>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="Convert_128767" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="self.conv1.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="384, 1, 1" offset="92160" size="384" />
			<output>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Convert_128770" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="self.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="self.conv1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 1, 1" offset="92544" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="self.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="8" name="self.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="9" name="__module.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
			<data strides="1" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>80</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>80</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="10" name="__module.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
			<data element_type="f32" shape="1, 384, 1" offset="93312" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="11" name="__module.conv1/aten::_convolution/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="47">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="12" name="aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="17,input.1">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
			</output>
		</layer>
		<layer id="13" name="self.conv2.weight" type="Const" version="opset1">
			<data element_type="u8" shape="384, 384, 3" offset="94848" size="442368" />
			<output>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="14" name="Convert_56328" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="15" name="self.conv2.weight/zero_point" type="Const" version="opset1">
			<data element_type="u8" shape="384, 1, 1" offset="537216" size="384" />
			<output>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="16" name="Convert_56331" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="U8">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="17" name="self.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="18" name="self.conv2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 1, 1" offset="537600" size="768" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="19" name="self.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="20" name="self.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="21" name="__module.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
			<data strides="2" dilations="1" pads_begin="1" pads_end="1" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>3000</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="22" name="__module.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
			<data element_type="f32" shape="1, 384, 1" offset="538368" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="23" name="__module.conv2/aten::_convolution/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>384</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="59">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="24" name="aten::gelu/Gelu_1" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="20,inputs_embeds.1">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
			</output>
		</layer>
		<layer id="25" name="Constant_116" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="539904" size="24" />
			<output>
				<port id="0" precision="I64" names="24">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="26" name="aten::permute/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>384</dim>
					<dim>1500</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="25,inputs_embeds">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="27" name="Constant_4657" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1500, 384" offset="539928" size="2304000" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="28" name="aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="27,input.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="29" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="30" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="31" name="Constant_4658" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="2843932" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="32" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="33" name="Constant_4659" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="2845468" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="34" name="__module.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="82,hidden_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="35" name="self.layers.0.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="2847004" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="36" name="Convert_69107" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="37" name="self.layers.0.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="2920732" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="38" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="39" name="Constant_69111" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="40" name="Reshape_69112" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="41" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="42" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="43" name="Constant_4660" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="2923052" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="44" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="91">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="45" name="Constant_4768" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="46" name="__module.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="93,query_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="47" name="__module.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="48" name="__module.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="94">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="49" name="self.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="2924636" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="50" name="Convert_64848" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="51" name="self.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="2998364" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="52" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="53" name="Constant_64852" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="54" name="Reshape_64853" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="55" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="56" name="__module.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="97">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="57" name="Constant_4769" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="58" name="__module.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="99,key_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="59" name="__module.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="60" name="__module.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="105">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="61" name="self.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="3000668" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="62" name="Convert_60589" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="63" name="self.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="3074396" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="64" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="65" name="Constant_60593" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="66" name="Reshape_60594" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="67" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="68" name="__module.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="69" name="Constant_4661" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3076700" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="70" name="__module.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="102">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="71" name="Constant_4770" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="72" name="__module.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="104,value_states.1">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="73" name="__module.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="74" name="__module.layers.0.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="107">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="75" name="__module.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>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="109,attn_output.1">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="76" name="__module.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="77" name="__module.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="110,attn_output.3">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="78" name="Constant_4771" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3078236" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="79" name="__module.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="112,input.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="80" name="self.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="3078260" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="81" name="Convert_73366" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="82" name="self.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="3151988" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="83" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="84" name="Constant_73370" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="85" name="Reshape_73371" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="86" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="87" name="__module.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="88" name="Constant_4662" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3154292" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="89" name="__module.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="115,input.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="90" name="__module.layers.0/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="117,input.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="91" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="92" name="__module.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="93" name="Constant_4663" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3155828" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="94" name="__module.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="95" name="Constant_4664" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3157364" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="96" name="__module.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="121,input.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="97" name="self.layers.0.fc1.weight" type="Const" version="opset1">
			<data element_type="i4" shape="1536, 3, 128" offset="3158900" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="98" name="Convert_22222" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="99" name="self.layers.0.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 3, 1" offset="3453812" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="100" name="self.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="101" name="Constant_22226" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3463028" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="102" name="Reshape_22227" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="103" name="self.layers.0.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="104" name="__module.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="105" name="Constant_4665" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1536" offset="3463044" size="6144" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="106" name="__module.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="124,input.15">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="107" name="__module.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="125,input.17">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="108" name="self.layers.0.fc2.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 12, 128" offset="3469188" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="109" name="Convert_26481" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="110" name="self.layers.0.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 12, 1" offset="3764100" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="111" name="self.layers.0.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="112" name="Constant_26485" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3773316" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="113" name="Reshape_26486" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="114" name="self.layers.0.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="115" name="__module.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="116" name="Constant_4666" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3773332" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="117" name="__module.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="129,input.21">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="118" name="__module.layers.0/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="131,input.23">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="119" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="120" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="121" name="Constant_4667" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3774868" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="122" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="123" name="Constant_4668" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3776404" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="124" name="__module.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="154,hidden_states.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="125" name="self.layers.1.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="3777940" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="126" name="Convert_86143" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="127" name="self.layers.1.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="3851668" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="128" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="129" name="Constant_86147" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="130" name="Reshape_86148" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="131" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="132" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="133" name="Constant_4669" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="3853972" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="134" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="163">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="135" name="Constant_4772" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="136" name="__module.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="165,query_states.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="137" name="__module.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="138" name="__module.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="166">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="139" name="self.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="3855508" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="140" name="Convert_81884" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="141" name="self.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="3929236" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="142" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="143" name="Constant_81888" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="144" name="Reshape_81889" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="145" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="146" name="__module.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="169">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="147" name="Constant_4773" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="148" name="__module.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="171,key_states.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="149" name="__module.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="150" name="__module.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="177">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="151" name="self.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="3931540" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="152" name="Convert_77625" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="153" name="self.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="4005268" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="154" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="155" name="Constant_77629" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="156" name="Reshape_77630" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="157" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="158" name="__module.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="159" name="Constant_4670" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4007572" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="160" name="__module.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="174">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="161" name="Constant_4774" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="162" name="__module.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="176,value_states.5">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="163" name="__module.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="164" name="__module.layers.1.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="179">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="165" name="__module.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>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="181,attn_output.5">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="166" name="__module.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="167" name="__module.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="182,attn_output.7">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="168" name="Constant_4775" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3078236" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="169" name="__module.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="184,input.25">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="170" name="self.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="4009108" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="171" name="Convert_90402" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="172" name="self.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="4082836" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="173" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="174" name="Constant_90406" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="175" name="Reshape_90407" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="176" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="177" name="__module.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="178" name="Constant_4671" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4085140" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="179" name="__module.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="187,input.27">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="180" name="__module.layers.1/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="189,input.29">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="181" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="182" name="__module.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="183" name="Constant_4672" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4086676" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="184" name="__module.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="185" name="Constant_4673" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4088212" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="186" name="__module.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="193,input.31">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="187" name="self.layers.1.fc1.weight" type="Const" version="opset1">
			<data element_type="i4" shape="1536, 3, 128" offset="4089748" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="188" name="Convert_30740" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="189" name="self.layers.1.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 3, 1" offset="4384660" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="190" name="self.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="191" name="Constant_30744" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3463028" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="192" name="Reshape_30745" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="193" name="self.layers.1.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="194" name="__module.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="195" name="Constant_4674" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1536" offset="4393876" size="6144" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="196" name="__module.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="196,input.33">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="197" name="__module.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="197,input.35">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="198" name="self.layers.1.fc2.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 12, 128" offset="4400020" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="199" name="Convert_34999" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="200" name="self.layers.1.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 12, 1" offset="4694932" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="201" name="self.layers.1.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="202" name="Constant_35003" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3773316" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="203" name="Reshape_35004" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="204" name="self.layers.1.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="205" name="__module.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="206" name="Constant_4675" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4704148" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="207" name="__module.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="201,input.39">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="208" name="__module.layers.1/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="203,input.41">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="209" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="210" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="211" name="Constant_4676" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4705684" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="212" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="213" name="Constant_4677" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4707220" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="214" name="__module.layers.2.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="226,hidden_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="215" name="self.layers.2.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="4708756" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="216" name="Convert_103179" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="217" name="self.layers.2.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="4782484" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="218" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="219" name="Constant_103183" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="220" name="Reshape_103184" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="221" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="222" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="223" name="Constant_4678" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4784788" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="224" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="235">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="225" name="Constant_4776" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="226" name="__module.layers.2.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="237,query_states.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="227" name="__module.layers.2.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="228" name="__module.layers.2.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="238">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="229" name="self.layers.2.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="4786324" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="230" name="Convert_98920" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="231" name="self.layers.2.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="4860052" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="232" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="233" name="Constant_98924" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="234" name="Reshape_98925" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="235" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="236" name="__module.layers.2.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="241">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="237" name="Constant_4777" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="238" name="__module.layers.2.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="243,key_states.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="239" name="__module.layers.2.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="240" name="__module.layers.2.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="249">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="241" name="self.layers.2.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="4862356" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="242" name="Convert_94661" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="243" name="self.layers.2.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="4936084" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="244" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="245" name="Constant_94665" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="246" name="Reshape_94666" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="247" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="248" name="__module.layers.2.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="249" name="Constant_4679" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="4938388" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="250" name="__module.layers.2.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="246">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="251" name="Constant_4778" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="252" name="__module.layers.2.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="248,value_states.9">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="253" name="__module.layers.2.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="254" name="__module.layers.2.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="251">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="255" name="__module.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>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="253,attn_output.9">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="256" name="__module.layers.2.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="257" name="__module.layers.2.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="254,attn_output.11">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="258" name="Constant_4779" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3078236" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="259" name="__module.layers.2.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="256,input.43">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="260" name="self.layers.2.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="4939924" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="261" name="Convert_107438" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="262" name="self.layers.2.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="5013652" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="263" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="264" name="Constant_107442" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="265" name="Reshape_107443" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="266" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="267" name="__module.layers.2.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="268" name="Constant_4680" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5015956" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="269" name="__module.layers.2.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="259,input.45">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="270" name="__module.layers.2/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="261,input.47">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="271" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="272" name="__module.layers.2.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="273" name="Constant_4681" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5017492" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="274" name="__module.layers.2.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="275" name="Constant_4682" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5019028" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="276" name="__module.layers.2.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="265,input.49">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="277" name="self.layers.2.fc1.weight" type="Const" version="opset1">
			<data element_type="i4" shape="1536, 3, 128" offset="5020564" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="278" name="Convert_39258" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="279" name="self.layers.2.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 3, 1" offset="5315476" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="280" name="self.layers.2.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="281" name="Constant_39262" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3463028" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="282" name="Reshape_39263" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="283" name="self.layers.2.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="284" name="__module.layers.2.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="285" name="Constant_4683" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1536" offset="5324692" size="6144" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="286" name="__module.layers.2.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="268,input.51">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="287" name="__module.layers.2.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="269,input.53">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="288" name="self.layers.2.fc2.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 12, 128" offset="5330836" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="289" name="Convert_43517" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="290" name="self.layers.2.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 12, 1" offset="5625748" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="291" name="self.layers.2.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="292" name="Constant_43521" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3773316" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="293" name="Reshape_43522" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="294" name="self.layers.2.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="295" name="__module.layers.2.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="296" name="Constant_4684" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5634964" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="297" name="__module.layers.2.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="273,input.57">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="298" name="__module.layers.2/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="275,input.59">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="299" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="300" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="301" name="Constant_4685" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5636500" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="302" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="303" name="Constant_4686" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5638036" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="304" name="__module.layers.3.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="298,hidden_states.19">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="305" name="self.layers.3.self_attn.q_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="5639572" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="306" name="Convert_120215" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="307" name="self.layers.3.self_attn.q_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="5713300" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="308" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="309" name="Constant_120219" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="310" name="Reshape_120220" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="311" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="312" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="313" name="Constant_4687" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5715604" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="314" name="__module.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>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="307">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="315" name="Constant_4780" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="316" name="__module.layers.3.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="309,query_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="317" name="__module.layers.3.self_attn/aten::transpose/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="318" name="__module.layers.3.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="310">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="319" name="self.layers.3.self_attn.k_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="5717140" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="320" name="Convert_115956" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="321" name="self.layers.3.self_attn.k_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="5790868" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="322" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="323" name="Constant_115960" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="324" name="Reshape_115961" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="325" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="326" name="__module.layers.3.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="313">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="327" name="Constant_4781" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="328" name="__module.layers.3.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="315,key_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="329" name="__module.layers.3.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="330" name="__module.layers.3.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="321">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="331" name="self.layers.3.self_attn.v_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="5793172" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="332" name="Convert_111697" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="333" name="self.layers.3.self_attn.v_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="5866900" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="334" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="335" name="Constant_111701" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="336" name="Reshape_111702" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="337" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="338" name="__module.layers.3.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="339" name="Constant_4688" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5869204" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="340" name="__module.layers.3.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="318">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="341" name="Constant_4782" type="Const" version="opset1">
			<data element_type="i64" shape="4" offset="2924588" size="32" />
			<output>
				<port id="0" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="342" name="__module.layers.3.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="320,value_states.13">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="343" name="__module.layers.3.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="344" name="__module.layers.3.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="323">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="345" name="__module.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>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="FP32" names="325,attn_output.13">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="346" name="__module.layers.3.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
			<data element_type="i32" shape="4" offset="2924620" size="16" />
			<output>
				<port id="0" precision="I32">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="347" name="__module.layers.3.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>6</dim>
					<dim>1500</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I32">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="326,attn_output">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
			</output>
		</layer>
		<layer id="348" name="Constant_4783" type="Const" version="opset1">
			<data element_type="i64" shape="3" offset="3078236" size="24" />
			<output>
				<port id="0" precision="I64">
					<dim>3</dim>
				</port>
			</output>
		</layer>
		<layer id="349" name="__module.layers.3.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
			<data special_zero="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>6</dim>
					<dim>64</dim>
				</port>
				<port id="1" precision="I64">
					<dim>3</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="328,input.61">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="350" name="self.layers.3.self_attn.out_proj.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 3, 128" offset="5870740" size="73728" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="351" name="Convert_124474" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="352" name="self.layers.3.self_attn.out_proj.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 3, 1" offset="5944468" size="2304" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="353" name="self.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>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="354" name="Constant_124478" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="2923036" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="355" name="Reshape_124479" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="356" name="self.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>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="357" name="__module.layers.3.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="358" name="Constant_4689" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5946772" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="359" name="__module.layers.3.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="331,input.63">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="360" name="__module.layers.3/aten::add/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="333,input.65">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="361" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="362" name="__module.layers.3.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="363" name="Constant_4690" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5948308" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="364" name="__module.layers.3.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="365" name="Constant_4691" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="5949844" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="366" name="__module.layers.3.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="337,input.67">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="367" name="self.layers.3.fc1.weight" type="Const" version="opset1">
			<data element_type="i4" shape="1536, 3, 128" offset="5951380" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="368" name="Convert_47776" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="369" name="self.layers.3.fc1.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="1536, 3, 1" offset="6246292" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="370" name="self.layers.3.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="371" name="Constant_47780" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3463028" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="372" name="Reshape_47781" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>3</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="373" name="self.layers.3.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="374" name="__module.layers.3.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1536</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="375" name="Constant_4692" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 1536" offset="6255508" size="6144" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="376" name="__module.layers.3.fc1/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="340,input.69">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="377" name="__module.layers.3.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
			<data approximation_mode="ERF" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="341,input.71">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="378" name="self.layers.3.fc2.weight" type="Const" version="opset1">
			<data element_type="i4" shape="384, 12, 128" offset="6261652" size="294912" />
			<output>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="379" name="Convert_52035" type="Convert" version="opset1">
			<data destination_type="f16" />
			<input>
				<port id="0" precision="I4">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="380" name="self.layers.3.fc2.weight/scale" type="Const" version="opset1">
			<data element_type="f16" shape="384, 12, 1" offset="6556564" size="9216" />
			<output>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="381" name="self.layers.3.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
			</output>
		</layer>
		<layer id="382" name="Constant_52039" type="Const" version="opset1">
			<data element_type="i64" shape="2" offset="3773316" size="16" />
			<output>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="383" name="Reshape_52040" type="Reshape" version="opset1">
			<data special_zero="false" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>12</dim>
					<dim>128</dim>
				</port>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="384" name="self.layers.3.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
			<data destination_type="f32" />
			<input>
				<port id="0" precision="FP16">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</output>
		</layer>
		<layer id="385" name="__module.layers.3.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
			<data transpose_a="false" transpose_b="true" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>1536</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>384</dim>
					<dim>1536</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="386" name="Constant_4693" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="6565780" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="387" name="__module.layers.3.fc2/aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="345,input.75">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="388" name="__module.layers.3/aten::add/Add_1" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="347,input">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="389" name="__module.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
			<data element_type="i32" shape="1" offset="2843928" size="4" />
			<output>
				<port id="0" precision="I32">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="390" name="__module.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="I32">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="391" name="Constant_4694" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="6567316" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="392" name="__module.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="393" name="Constant_4695" type="Const" version="opset1">
			<data element_type="f32" shape="1, 1, 384" offset="6568852" size="1536" />
			<output>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="394" name="__module.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>1</dim>
					<dim>384</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="last_hidden_state">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</output>
		</layer>
		<layer id="395" name="Result_1350" type="Result" version="opset1" output_names="last_hidden_state">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>1500</dim>
					<dim>384</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="9" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
		<edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
		<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
		<edge from-layer="4" from-port="1" to-layer="5" to-port="1" />
		<edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
		<edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
		<edge from-layer="7" from-port="2" to-layer="8" to-port="0" />
		<edge from-layer="8" from-port="1" to-layer="9" to-port="1" />
		<edge from-layer="9" from-port="2" to-layer="11" to-port="0" />
		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
		<edge from-layer="11" from-port="2" to-layer="12" to-port="0" />
		<edge from-layer="12" from-port="1" to-layer="21" to-port="0" />
		<edge from-layer="13" from-port="0" to-layer="14" to-port="0" />
		<edge from-layer="14" from-port="1" to-layer="17" to-port="0" />
		<edge from-layer="15" from-port="0" to-layer="16" to-port="0" />
		<edge from-layer="16" from-port="1" to-layer="17" to-port="1" />
		<edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
		<edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
		<edge from-layer="19" from-port="2" to-layer="20" to-port="0" />
		<edge from-layer="20" from-port="1" to-layer="21" to-port="1" />
		<edge from-layer="21" from-port="2" to-layer="23" to-port="0" />
		<edge from-layer="22" from-port="0" to-layer="23" to-port="1" />
		<edge from-layer="23" from-port="2" to-layer="24" to-port="0" />
		<edge from-layer="24" from-port="1" to-layer="26" to-port="0" />
		<edge from-layer="25" from-port="0" to-layer="26" to-port="1" />
		<edge from-layer="26" from-port="2" to-layer="28" 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="30" to-port="0" />
		<edge from-layer="28" from-port="2" to-layer="90" to-port="0" />
		<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
		<edge from-layer="30" from-port="2" to-layer="32" to-port="0" />
		<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
		<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
		<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
		<edge from-layer="34" from-port="2" to-layer="68" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="56" to-port="0" />
		<edge from-layer="34" from-port="2" to-layer="42" to-port="0" />
		<edge from-layer="35" from-port="0" to-layer="36" to-port="0" />
		<edge from-layer="36" from-port="1" to-layer="38" to-port="0" />
		<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
		<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
		<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
		<edge from-layer="40" from-port="2" to-layer="41" to-port="0" />
		<edge from-layer="41" from-port="1" to-layer="42" to-port="1" />
		<edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
		<edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
		<edge from-layer="44" from-port="2" to-layer="46" to-port="0" />
		<edge from-layer="45" from-port="0" to-layer="46" to-port="1" />
		<edge from-layer="46" from-port="2" to-layer="48" to-port="0" />
		<edge from-layer="47" from-port="0" to-layer="48" to-port="1" />
		<edge from-layer="48" from-port="2" to-layer="75" to-port="0" />
		<edge from-layer="49" from-port="0" to-layer="50" to-port="0" />
		<edge from-layer="50" from-port="1" to-layer="52" to-port="0" />
		<edge from-layer="51" from-port="0" to-layer="52" to-port="1" />
		<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
		<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
		<edge from-layer="54" from-port="2" to-layer="55" to-port="0" />
		<edge from-layer="55" from-port="1" 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="60" to-port="0" />
		<edge from-layer="59" from-port="0" to-layer="60" to-port="1" />
		<edge from-layer="60" from-port="2" to-layer="75" to-port="1" />
		<edge from-layer="61" from-port="0" to-layer="62" to-port="0" />
		<edge from-layer="62" from-port="1" to-layer="64" to-port="0" />
		<edge from-layer="63" from-port="0" to-layer="64" to-port="1" />
		<edge from-layer="64" from-port="2" to-layer="66" to-port="0" />
		<edge from-layer="65" from-port="0" to-layer="66" to-port="1" />
		<edge from-layer="66" from-port="2" to-layer="67" to-port="0" />
		<edge from-layer="67" from-port="1" to-layer="68" to-port="1" />
		<edge from-layer="68" from-port="2" to-layer="70" to-port="0" />
		<edge from-layer="69" from-port="0" to-layer="70" to-port="1" />
		<edge from-layer="70" from-port="2" to-layer="72" to-port="0" />
		<edge from-layer="71" from-port="0" to-layer="72" to-port="1" />
		<edge from-layer="72" from-port="2" to-layer="74" to-port="0" />
		<edge from-layer="73" from-port="0" to-layer="74" to-port="1" />
		<edge from-layer="74" from-port="2" to-layer="75" to-port="2" />
		<edge from-layer="75" from-port="3" to-layer="77" to-port="0" />
		<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
		<edge from-layer="77" from-port="2" to-layer="79" to-port="0" />
		<edge from-layer="78" from-port="0" to-layer="79" to-port="1" />
		<edge from-layer="79" from-port="2" to-layer="87" to-port="0" />
		<edge from-layer="80" from-port="0" to-layer="81" to-port="0" />
		<edge from-layer="81" from-port="1" to-layer="83" to-port="0" />
		<edge from-layer="82" from-port="0" to-layer="83" to-port="1" />
		<edge from-layer="83" from-port="2" to-layer="85" to-port="0" />
		<edge from-layer="84" from-port="0" to-layer="85" to-port="1" />
		<edge from-layer="85" from-port="2" to-layer="86" to-port="0" />
		<edge from-layer="86" from-port="1" to-layer="87" to-port="1" />
		<edge from-layer="87" from-port="2" to-layer="89" to-port="0" />
		<edge from-layer="88" from-port="0" to-layer="89" to-port="1" />
		<edge from-layer="89" from-port="2" to-layer="90" to-port="1" />
		<edge from-layer="90" from-port="2" to-layer="118" to-port="0" />
		<edge from-layer="90" from-port="2" to-layer="92" to-port="0" />
		<edge from-layer="91" from-port="0" to-layer="92" to-port="1" />
		<edge from-layer="92" from-port="2" to-layer="94" to-port="0" />
		<edge from-layer="93" from-port="0" to-layer="94" to-port="1" />
		<edge from-layer="94" from-port="2" to-layer="96" to-port="0" />
		<edge from-layer="95" from-port="0" to-layer="96" to-port="1" />
		<edge from-layer="96" from-port="2" to-layer="104" to-port="0" />
		<edge from-layer="97" from-port="0" to-layer="98" to-port="0" />
		<edge from-layer="98" from-port="1" 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="102" to-port="0" />
		<edge from-layer="101" from-port="0" to-layer="102" to-port="1" />
		<edge from-layer="102" from-port="2" to-layer="103" to-port="0" />
		<edge from-layer="103" from-port="1" to-layer="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="107" to-port="0" />
		<edge from-layer="107" from-port="1" to-layer="115" to-port="0" />
		<edge from-layer="108" from-port="0" to-layer="109" to-port="0" />
		<edge from-layer="109" from-port="1" to-layer="111" to-port="0" />
		<edge from-layer="110" from-port="0" to-layer="111" to-port="1" />
		<edge from-layer="111" from-port="2" to-layer="113" to-port="0" />
		<edge from-layer="112" from-port="0" to-layer="113" to-port="1" />
		<edge from-layer="113" from-port="2" to-layer="114" to-port="0" />
		<edge from-layer="114" from-port="1" to-layer="115" to-port="1" />
		<edge from-layer="115" from-port="2" to-layer="117" to-port="0" />
		<edge from-layer="116" from-port="0" to-layer="117" to-port="1" />
		<edge from-layer="117" from-port="2" to-layer="118" to-port="1" />
		<edge from-layer="118" from-port="2" to-layer="120" to-port="0" />
		<edge from-layer="118" from-port="2" to-layer="180" to-port="0" />
		<edge from-layer="119" from-port="0" to-layer="120" to-port="1" />
		<edge from-layer="120" from-port="2" to-layer="122" to-port="0" />
		<edge from-layer="121" from-port="0" to-layer="122" to-port="1" />
		<edge from-layer="122" from-port="2" to-layer="124" to-port="0" />
		<edge from-layer="123" from-port="0" to-layer="124" to-port="1" />
		<edge from-layer="124" from-port="2" to-layer="158" to-port="0" />
		<edge from-layer="124" from-port="2" to-layer="132" to-port="0" />
		<edge from-layer="124" from-port="2" to-layer="146" to-port="0" />
		<edge from-layer="125" from-port="0" to-layer="126" to-port="0" />
		<edge from-layer="126" from-port="1" to-layer="128" to-port="0" />
		<edge from-layer="127" from-port="0" to-layer="128" to-port="1" />
		<edge from-layer="128" from-port="2" to-layer="130" to-port="0" />
		<edge from-layer="129" from-port="0" to-layer="130" to-port="1" />
		<edge from-layer="130" from-port="2" to-layer="131" to-port="0" />
		<edge from-layer="131" from-port="1" to-layer="132" to-port="1" />
		<edge from-layer="132" from-port="2" to-layer="134" to-port="0" />
		<edge from-layer="133" from-port="0" to-layer="134" to-port="1" />
		<edge from-layer="134" from-port="2" to-layer="136" to-port="0" />
		<edge from-layer="135" from-port="0" to-layer="136" to-port="1" />
		<edge from-layer="136" from-port="2" to-layer="138" to-port="0" />
		<edge from-layer="137" from-port="0" to-layer="138" to-port="1" />
		<edge from-layer="138" from-port="2" to-layer="165" to-port="0" />
		<edge from-layer="139" from-port="0" to-layer="140" to-port="0" />
		<edge from-layer="140" from-port="1" to-layer="142" to-port="0" />
		<edge from-layer="141" from-port="0" to-layer="142" to-port="1" />
		<edge from-layer="142" from-port="2" to-layer="144" to-port="0" />
		<edge from-layer="143" from-port="0" to-layer="144" to-port="1" />
		<edge from-layer="144" from-port="2" to-layer="145" to-port="0" />
		<edge from-layer="145" from-port="1" to-layer="146" to-port="1" />
		<edge from-layer="146" from-port="2" to-layer="148" to-port="0" />
		<edge from-layer="147" from-port="0" to-layer="148" to-port="1" />
		<edge from-layer="148" from-port="2" to-layer="150" to-port="0" />
		<edge from-layer="149" from-port="0" to-layer="150" to-port="1" />
		<edge from-layer="150" from-port="2" to-layer="165" to-port="1" />
		<edge from-layer="151" from-port="0" to-layer="152" to-port="0" />
		<edge from-layer="152" from-port="1" to-layer="154" to-port="0" />
		<edge from-layer="153" from-port="0" to-layer="154" to-port="1" />
		<edge from-layer="154" from-port="2" to-layer="156" to-port="0" />
		<edge from-layer="155" from-port="0" to-layer="156" to-port="1" />
		<edge from-layer="156" from-port="2" to-layer="157" to-port="0" />
		<edge from-layer="157" from-port="1" to-layer="158" to-port="1" />
		<edge from-layer="158" from-port="2" to-layer="160" to-port="0" />
		<edge from-layer="159" from-port="0" to-layer="160" to-port="1" />
		<edge from-layer="160" from-port="2" to-layer="162" to-port="0" />
		<edge from-layer="161" from-port="0" to-layer="162" to-port="1" />
		<edge from-layer="162" from-port="2" to-layer="164" to-port="0" />
		<edge from-layer="163" from-port="0" to-layer="164" to-port="1" />
		<edge from-layer="164" from-port="2" to-layer="165" to-port="2" />
		<edge from-layer="165" from-port="3" to-layer="167" to-port="0" />
		<edge from-layer="166" from-port="0" to-layer="167" to-port="1" />
		<edge from-layer="167" from-port="2" to-layer="169" to-port="0" />
		<edge from-layer="168" from-port="0" to-layer="169" to-port="1" />
		<edge from-layer="169" from-port="2" to-layer="177" to-port="0" />
		<edge from-layer="170" from-port="0" to-layer="171" to-port="0" />
		<edge from-layer="171" from-port="1" to-layer="173" to-port="0" />
		<edge from-layer="172" from-port="0" to-layer="173" to-port="1" />
		<edge from-layer="173" from-port="2" to-layer="175" to-port="0" />
		<edge from-layer="174" from-port="0" to-layer="175" to-port="1" />
		<edge from-layer="175" from-port="2" to-layer="176" to-port="0" />
		<edge from-layer="176" from-port="1" 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="180" to-port="1" />
		<edge from-layer="180" from-port="2" to-layer="182" to-port="0" />
		<edge from-layer="180" from-port="2" to-layer="208" to-port="0" />
		<edge from-layer="181" from-port="0" to-layer="182" to-port="1" />
		<edge from-layer="182" from-port="2" to-layer="184" to-port="0" />
		<edge from-layer="183" from-port="0" to-layer="184" to-port="1" />
		<edge from-layer="184" from-port="2" to-layer="186" to-port="0" />
		<edge from-layer="185" from-port="0" to-layer="186" to-port="1" />
		<edge from-layer="186" from-port="2" to-layer="194" to-port="0" />
		<edge from-layer="187" from-port="0" to-layer="188" to-port="0" />
		<edge from-layer="188" from-port="1" 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="192" to-port="0" />
		<edge from-layer="191" from-port="0" to-layer="192" to-port="1" />
		<edge from-layer="192" from-port="2" to-layer="193" to-port="0" />
		<edge from-layer="193" from-port="1" to-layer="194" to-port="1" />
		<edge from-layer="194" from-port="2" to-layer="196" to-port="0" />
		<edge from-layer="195" from-port="0" to-layer="196" to-port="1" />
		<edge from-layer="196" from-port="2" to-layer="197" to-port="0" />
		<edge from-layer="197" from-port="1" to-layer="205" to-port="0" />
		<edge from-layer="198" from-port="0" to-layer="199" to-port="0" />
		<edge from-layer="199" from-port="1" 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="204" to-port="0" />
		<edge from-layer="204" from-port="1" to-layer="205" to-port="1" />
		<edge from-layer="205" from-port="2" to-layer="207" to-port="0" />
		<edge from-layer="206" from-port="0" to-layer="207" to-port="1" />
		<edge from-layer="207" from-port="2" to-layer="208" to-port="1" />
		<edge from-layer="208" from-port="2" to-layer="270" to-port="0" />
		<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="214" to-port="0" />
		<edge from-layer="213" from-port="0" to-layer="214" to-port="1" />
		<edge from-layer="214" from-port="2" to-layer="248" to-port="0" />
		<edge from-layer="214" from-port="2" to-layer="236" to-port="0" />
		<edge from-layer="214" from-port="2" to-layer="222" to-port="0" />
		<edge from-layer="215" from-port="0" to-layer="216" to-port="0" />
		<edge from-layer="216" from-port="1" to-layer="218" to-port="0" />
		<edge from-layer="217" from-port="0" to-layer="218" to-port="1" />
		<edge from-layer="218" from-port="2" to-layer="220" to-port="0" />
		<edge from-layer="219" from-port="0" to-layer="220" to-port="1" />
		<edge from-layer="220" from-port="2" to-layer="221" to-port="0" />
		<edge from-layer="221" from-port="1" to-layer="222" to-port="1" />
		<edge from-layer="222" from-port="2" to-layer="224" to-port="0" />
		<edge from-layer="223" from-port="0" to-layer="224" to-port="1" />
		<edge from-layer="224" from-port="2" to-layer="226" to-port="0" />
		<edge from-layer="225" from-port="0" to-layer="226" to-port="1" />
		<edge from-layer="226" from-port="2" to-layer="228" to-port="0" />
		<edge from-layer="227" from-port="0" to-layer="228" to-port="1" />
		<edge from-layer="228" from-port="2" to-layer="255" to-port="0" />
		<edge from-layer="229" from-port="0" to-layer="230" to-port="0" />
		<edge from-layer="230" from-port="1" to-layer="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="234" to-port="0" />
		<edge from-layer="233" from-port="0" to-layer="234" to-port="1" />
		<edge from-layer="234" from-port="2" to-layer="235" to-port="0" />
		<edge from-layer="235" from-port="1" to-layer="236" to-port="1" />
		<edge from-layer="236" from-port="2" to-layer="238" to-port="0" />
		<edge from-layer="237" from-port="0" to-layer="238" to-port="1" />
		<edge from-layer="238" from-port="2" to-layer="240" to-port="0" />
		<edge from-layer="239" from-port="0" to-layer="240" to-port="1" />
		<edge from-layer="240" from-port="2" to-layer="255" to-port="1" />
		<edge from-layer="241" from-port="0" to-layer="242" to-port="0" />
		<edge from-layer="242" from-port="1" 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="252" to-port="0" />
		<edge from-layer="251" from-port="0" to-layer="252" to-port="1" />
		<edge from-layer="252" from-port="2" to-layer="254" to-port="0" />
		<edge from-layer="253" from-port="0" to-layer="254" to-port="1" />
		<edge from-layer="254" from-port="2" to-layer="255" to-port="2" />
		<edge from-layer="255" from-port="3" to-layer="257" to-port="0" />
		<edge from-layer="256" from-port="0" to-layer="257" to-port="1" />
		<edge from-layer="257" from-port="2" to-layer="259" to-port="0" />
		<edge from-layer="258" from-port="0" to-layer="259" to-port="1" />
		<edge from-layer="259" from-port="2" to-layer="267" 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="263" to-port="0" />
		<edge from-layer="262" from-port="0" to-layer="263" to-port="1" />
		<edge from-layer="263" from-port="2" to-layer="265" to-port="0" />
		<edge from-layer="264" from-port="0" to-layer="265" to-port="1" />
		<edge from-layer="265" from-port="2" to-layer="266" to-port="0" />
		<edge from-layer="266" from-port="1" to-layer="267" to-port="1" />
		<edge from-layer="267" from-port="2" to-layer="269" to-port="0" />
		<edge from-layer="268" from-port="0" to-layer="269" to-port="1" />
		<edge from-layer="269" from-port="2" to-layer="270" to-port="1" />
		<edge from-layer="270" from-port="2" to-layer="272" to-port="0" />
		<edge from-layer="270" from-port="2" to-layer="298" 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="276" to-port="0" />
		<edge from-layer="275" from-port="0" to-layer="276" to-port="1" />
		<edge from-layer="276" from-port="2" to-layer="284" 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="280" to-port="0" />
		<edge from-layer="279" from-port="0" to-layer="280" to-port="1" />
		<edge from-layer="280" from-port="2" to-layer="282" to-port="0" />
		<edge from-layer="281" from-port="0" to-layer="282" to-port="1" />
		<edge from-layer="282" from-port="2" to-layer="283" to-port="0" />
		<edge from-layer="283" from-port="1" to-layer="284" to-port="1" />
		<edge from-layer="284" from-port="2" to-layer="286" to-port="0" />
		<edge from-layer="285" from-port="0" to-layer="286" to-port="1" />
		<edge from-layer="286" from-port="2" to-layer="287" to-port="0" />
		<edge from-layer="287" from-port="1" to-layer="295" to-port="0" />
		<edge from-layer="288" from-port="0" to-layer="289" to-port="0" />
		<edge from-layer="289" from-port="1" to-layer="291" to-port="0" />
		<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
		<edge from-layer="291" from-port="2" to-layer="293" to-port="0" />
		<edge from-layer="292" from-port="0" to-layer="293" to-port="1" />
		<edge from-layer="293" from-port="2" to-layer="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="298" to-port="1" />
		<edge from-layer="298" from-port="2" to-layer="360" to-port="0" />
		<edge from-layer="298" from-port="2" to-layer="300" to-port="0" />
		<edge from-layer="299" from-port="0" to-layer="300" to-port="1" />
		<edge from-layer="300" from-port="2" to-layer="302" to-port="0" />
		<edge from-layer="301" from-port="0" to-layer="302" to-port="1" />
		<edge from-layer="302" from-port="2" to-layer="304" to-port="0" />
		<edge from-layer="303" from-port="0" to-layer="304" to-port="1" />
		<edge from-layer="304" from-port="2" to-layer="338" to-port="0" />
		<edge from-layer="304" from-port="2" to-layer="326" to-port="0" />
		<edge from-layer="304" from-port="2" to-layer="312" to-port="0" />
		<edge from-layer="305" from-port="0" to-layer="306" to-port="0" />
		<edge from-layer="306" from-port="1" to-layer="308" to-port="0" />
		<edge from-layer="307" from-port="0" to-layer="308" to-port="1" />
		<edge from-layer="308" from-port="2" to-layer="310" to-port="0" />
		<edge from-layer="309" from-port="0" to-layer="310" to-port="1" />
		<edge from-layer="310" from-port="2" to-layer="311" to-port="0" />
		<edge from-layer="311" from-port="1" to-layer="312" to-port="1" />
		<edge from-layer="312" from-port="2" to-layer="314" to-port="0" />
		<edge from-layer="313" from-port="0" to-layer="314" to-port="1" />
		<edge from-layer="314" from-port="2" to-layer="316" to-port="0" />
		<edge from-layer="315" from-port="0" to-layer="316" to-port="1" />
		<edge from-layer="316" from-port="2" to-layer="318" to-port="0" />
		<edge from-layer="317" from-port="0" to-layer="318" to-port="1" />
		<edge from-layer="318" from-port="2" to-layer="345" to-port="0" />
		<edge from-layer="319" from-port="0" to-layer="320" to-port="0" />
		<edge from-layer="320" from-port="1" 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="324" to-port="0" />
		<edge from-layer="323" from-port="0" to-layer="324" to-port="1" />
		<edge from-layer="324" from-port="2" to-layer="325" to-port="0" />
		<edge from-layer="325" from-port="1" to-layer="326" to-port="1" />
		<edge from-layer="326" from-port="2" to-layer="328" to-port="0" />
		<edge from-layer="327" from-port="0" to-layer="328" to-port="1" />
		<edge from-layer="328" from-port="2" to-layer="330" to-port="0" />
		<edge from-layer="329" from-port="0" to-layer="330" to-port="1" />
		<edge from-layer="330" from-port="2" to-layer="345" to-port="1" />
		<edge from-layer="331" from-port="0" to-layer="332" to-port="0" />
		<edge from-layer="332" from-port="1" to-layer="334" to-port="0" />
		<edge from-layer="333" from-port="0" to-layer="334" to-port="1" />
		<edge from-layer="334" from-port="2" to-layer="336" to-port="0" />
		<edge from-layer="335" from-port="0" to-layer="336" to-port="1" />
		<edge from-layer="336" from-port="2" to-layer="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="344" to-port="0" />
		<edge from-layer="343" from-port="0" to-layer="344" to-port="1" />
		<edge from-layer="344" from-port="2" to-layer="345" to-port="2" />
		<edge from-layer="345" from-port="3" to-layer="347" to-port="0" />
		<edge from-layer="346" from-port="0" to-layer="347" to-port="1" />
		<edge from-layer="347" from-port="2" to-layer="349" to-port="0" />
		<edge from-layer="348" from-port="0" to-layer="349" to-port="1" />
		<edge from-layer="349" from-port="2" to-layer="357" to-port="0" />
		<edge from-layer="350" from-port="0" to-layer="351" to-port="0" />
		<edge from-layer="351" from-port="1" 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="356" to-port="0" />
		<edge from-layer="356" from-port="1" to-layer="357" to-port="1" />
		<edge from-layer="357" from-port="2" to-layer="359" to-port="0" />
		<edge from-layer="358" from-port="0" to-layer="359" to-port="1" />
		<edge from-layer="359" from-port="2" to-layer="360" to-port="1" />
		<edge from-layer="360" from-port="2" to-layer="388" to-port="0" />
		<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="366" to-port="0" />
		<edge from-layer="365" from-port="0" to-layer="366" to-port="1" />
		<edge from-layer="366" from-port="2" to-layer="374" to-port="0" />
		<edge from-layer="367" from-port="0" to-layer="368" to-port="0" />
		<edge from-layer="368" from-port="1" to-layer="370" to-port="0" />
		<edge from-layer="369" from-port="0" to-layer="370" to-port="1" />
		<edge from-layer="370" from-port="2" to-layer="372" to-port="0" />
		<edge from-layer="371" from-port="0" to-layer="372" to-port="1" />
		<edge from-layer="372" from-port="2" to-layer="373" to-port="0" />
		<edge from-layer="373" from-port="1" to-layer="374" to-port="1" />
		<edge from-layer="374" from-port="2" to-layer="376" to-port="0" />
		<edge from-layer="375" from-port="0" to-layer="376" to-port="1" />
		<edge from-layer="376" from-port="2" to-layer="377" to-port="0" />
		<edge from-layer="377" from-port="1" to-layer="385" 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="381" to-port="0" />
		<edge from-layer="380" from-port="0" to-layer="381" to-port="1" />
		<edge from-layer="381" from-port="2" to-layer="383" to-port="0" />
		<edge from-layer="382" from-port="0" to-layer="383" to-port="1" />
		<edge from-layer="383" from-port="2" to-layer="384" to-port="0" />
		<edge from-layer="384" from-port="1" to-layer="385" to-port="1" />
		<edge from-layer="385" from-port="2" to-layer="387" to-port="0" />
		<edge from-layer="386" from-port="0" to-layer="387" to-port="1" />
		<edge from-layer="387" from-port="2" to-layer="388" to-port="1" />
		<edge from-layer="388" from-port="2" to-layer="390" to-port="0" />
		<edge from-layer="389" from-port="0" to-layer="390" to-port="1" />
		<edge from-layer="390" from-port="2" to-layer="392" to-port="0" />
		<edge from-layer="391" from-port="0" to-layer="392" to-port="1" />
		<edge from-layer="392" from-port="2" to-layer="394" to-port="0" />
		<edge from-layer="393" from-port="0" to-layer="394" to-port="1" />
		<edge from-layer="394" from-port="2" to-layer="395" 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="True" />
				<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_sym" />
				<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>