diff --git "a/vae_encoder/openvino_model.xml" "b/vae_encoder/openvino_model.xml"
--- "a/vae_encoder/openvino_model.xml"
+++ "b/vae_encoder/openvino_model.xml"
@@ -12,10 +12,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="1" name="self.encoder.conv_in.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="128, 3, 3, 3" offset="0" size="6912" />
+		<layer id="1" name="self.encoder.conv_in.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 3, 3, 3" offset="0" size="3456" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.conv_in.weight">
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>3</dim>
 					<dim>3</dim>
@@ -23,13 +23,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="2" name="self.encoder.conv_in.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="2" name="Convert_123794" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>3</dim>
 					<dim>3</dim>
@@ -37,7 +34,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>3</dim>
 					<dim>3</dim>
@@ -45,151 +42,195 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="3" name="__module.encoder.conv_in/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>3</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>128</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
-			</input>
+		<layer id="3" name="self.encoder.conv_in.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 1, 1, 1" offset="3456" size="128" />
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="4" name="__module.encoder.conv_in/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="6912" size="256" />
-			<output>
-				<port id="0" precision="FP16">
+		<layer id="4" name="Convert_123797" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="5" name="__module.encoder.conv_in/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="5" name="self.encoder.conv_in.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>128</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="2" precision="FP16">
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="self.encoder.conv_in.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="128, 1, 1, 1" offset="3584" size="256" />
+			<output>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="6" name="__module.encoder.conv_in/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="7" name="self.encoder.conv_in.weight/fq_weights_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="92,input.1">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="7" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="8" name="self.encoder.conv_in.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="8" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="9" name="__module.encoder.conv_in/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>128</dim>
+					<dim>3</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</input>
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="9" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="10" name="__module.encoder.conv_in/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 128, 1, 1" offset="3840" size="512" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>128</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="10" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="11" name="__module.encoder.conv_in/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>128</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="47,input.1">
+					<dim>-1</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="11" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="12" name="self.encoder.down_blocks.0.resnets.0.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="4352" size="512" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.0.norm1.weight">
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="self.encoder.down_blocks.0.resnets.0.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="4864" size="512" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.0.norm1.bias">
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -197,27 +238,33 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>128</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="3" precision="FP32" names="61,input.3">
+					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="12" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="15" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="1" precision="FP32" names="62">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -225,144 +272,120 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="13" name="Constant_624600_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="7184" size="256" />
+		<layer id="16" name="self.encoder.down_blocks.0.resnets.0.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 128, 3, 3" offset="5376" size="147456" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="14" name="Constant_624600" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="15" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="17" name="Convert_123706" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="16" name="Constant_624601_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="7440" size="256" />
+		<layer id="18" name="self.encoder.down_blocks.0.resnets.0.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 1, 1, 1" offset="152832" size="128" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="17" name="Constant_624601" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="19" name="Convert_123709" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="18" name="__module.encoder.down_blocks.0.resnets.0.norm1/aten::group_norm/Add" type="Add" version="opset1">
+		<layer id="20" name="self.encoder.down_blocks.0.resnets.0.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="106,input.3">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="19" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
+		<layer id="21" name="self.encoder.down_blocks.0.resnets.0.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="128, 1, 1, 1" offset="152960" size="256" />
 			<output>
-				<port id="1" precision="FP32" names="107">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="20" name="self.encoder.down_blocks.0.resnets.0.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="128, 128, 3, 3" offset="7696" size="294912" />
+		<layer id="22" name="self.encoder.down_blocks.0.resnets.0.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>128</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.0.resnets.0.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -370,11 +393,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="21" name="self.encoder.down_blocks.0.resnets.0.conv1.weight" type="Convert" version="opset1">
+		<layer id="23" name="self.encoder.down_blocks.0.resnets.0.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>128</dim>
@@ -392,7 +412,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="22" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="24" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -417,10 +437,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="23" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="302608" size="256" />
+		<layer id="25" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 128, 1, 1" offset="153216" size="512" />
 			<output>
-				<port id="0" precision="FP16">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
@@ -428,66 +448,49 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="24" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="26" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
-			</input>
-			<output>
 				<port id="1" precision="FP32">
 					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="25" name="__module.encoder.down_blocks.0.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="69,input.5">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="27" name="self.encoder.down_blocks.0.resnets.0.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="153728" size="512" />
 			<output>
-				<port id="2" precision="FP32" names="114,input.5">
-					<dim>-1</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.0.norm2.weight">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="26" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="28" name="self.encoder.down_blocks.0.resnets.0.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="154240" size="512" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.0.norm2.bias">
+					<dim>128</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="27" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="29" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -495,221 +498,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>128</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="72,input.7">
+					<dim>-1</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="28" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="29" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="30" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_1" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="30" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="73,input.9">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="31" name="self.encoder.down_blocks.0.resnets.0.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 128, 3, 3" offset="154752" size="147456" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="31" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="32" name="Convert_123717" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="32" name="Constant_624602_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="302864" size="256" />
+		<layer id="33" name="self.encoder.down_blocks.0.resnets.0.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 1, 1, 1" offset="302208" size="128" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="33" name="Constant_624602" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="34" name="Convert_123720" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="34" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="35" name="self.encoder.down_blocks.0.resnets.0.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="35" name="Constant_624603_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="303120" size="256" />
+		<layer id="36" name="self.encoder.down_blocks.0.resnets.0.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="128, 1, 1, 1" offset="302336" size="256" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="36" name="Constant_624603" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="37" name="self.encoder.down_blocks.0.resnets.0.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="37" name="__module.encoder.down_blocks.0.resnets.0.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="117,input.7">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="38" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_1" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="118,input.9">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="39" name="self.encoder.down_blocks.0.resnets.0.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="128, 128, 3, 3" offset="303376" size="294912" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.0.resnets.0.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -717,11 +653,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="40" name="self.encoder.down_blocks.0.resnets.0.conv2.weight" type="Convert" version="opset1">
+		<layer id="38" name="self.encoder.down_blocks.0.resnets.0.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>128</dim>
@@ -739,7 +672,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="41" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="39" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -764,32 +697,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="42" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="598288" size="256" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="43" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="40" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 128, 1, 1" offset="302592" size="512" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
@@ -797,7 +708,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="44" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="41" name="__module.encoder.down_blocks.0.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -814,7 +725,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="126,hidden_states.1">
+				<port id="2" precision="FP32" names="81,hidden_states.1">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -822,7 +733,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="45" name="__module.encoder.down_blocks.0.resnets.0/aten::add/Add" type="Add" version="opset1">
+		<layer id="42" name="__module.encoder.down_blocks.0.resnets.0/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -839,7 +750,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="127,128,input.11">
+				<port id="2" precision="FP32" names="82,83,input.11">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -847,19 +758,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="46" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="43" name="self.encoder.down_blocks.0.resnets.1.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="303104" size="512" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.1.norm1.weight">
+					<dim>128</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="47" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="44" name="self.encoder.down_blocks.0.resnets.1.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="303616" size="512" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.1.norm1.bias">
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -867,221 +783,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>128</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="91,input.13">
+					<dim>-1</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="48" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="49" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="46" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_2" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="50" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="92">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="47" name="self.encoder.down_blocks.0.resnets.1.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 128, 3, 3" offset="304128" size="147456" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="51" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="48" name="Convert_123728" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="52" name="Constant_624604_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="598544" size="256" />
+		<layer id="49" name="self.encoder.down_blocks.0.resnets.1.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 1, 1, 1" offset="451584" size="128" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="53" name="Constant_624604" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="50" name="Convert_123731" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="54" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="51" name="self.encoder.down_blocks.0.resnets.1.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="55" name="Constant_624605_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="598800" size="256" />
+		<layer id="52" name="self.encoder.down_blocks.0.resnets.1.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="128, 1, 1, 1" offset="451712" size="256" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="56" name="Constant_624605" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="53" name="self.encoder.down_blocks.0.resnets.1.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="57" name="__module.encoder.down_blocks.0.resnets.1.norm1/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="136,input.13">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="58" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_2" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="137">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="59" name="self.encoder.down_blocks.0.resnets.1.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="128, 128, 3, 3" offset="599056" size="294912" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.0.resnets.1.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -1089,11 +938,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="60" name="self.encoder.down_blocks.0.resnets.1.conv1.weight" type="Convert" version="opset1">
+		<layer id="54" name="self.encoder.down_blocks.0.resnets.1.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>128</dim>
@@ -1111,7 +957,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="61" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="55" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -1136,32 +982,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="62" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="893968" size="256" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="63" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="56" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 128, 1, 1" offset="451968" size="512" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
@@ -1169,7 +993,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="64" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="57" name="__module.encoder.down_blocks.0.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -1186,7 +1010,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="144,input.15">
+				<port id="2" precision="FP32" names="99,input.15">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -1194,19 +1018,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="65" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="58" name="self.encoder.down_blocks.0.resnets.1.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="452480" size="512" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.1.norm2.weight">
+					<dim>128</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="66" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="59" name="self.encoder.down_blocks.0.resnets.1.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="452992" size="512" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.0.resnets.1.norm2.bias">
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="60" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -1214,221 +1043,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>128</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="102,input.17">
+					<dim>-1</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="67" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="68" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="61" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_3" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="69" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="103,input.19">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="62" name="self.encoder.down_blocks.0.resnets.1.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 128, 3, 3" offset="453504" size="147456" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="70" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="63" name="Convert_123739" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="71" name="Constant_624606_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="894224" size="256" />
+		<layer id="64" name="self.encoder.down_blocks.0.resnets.1.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 1, 1, 1" offset="600960" size="128" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="72" name="Constant_624606" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="65" name="Convert_123742" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="73" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="66" name="self.encoder.down_blocks.0.resnets.1.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="74" name="Constant_624607_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="894480" size="256" />
+		<layer id="67" name="self.encoder.down_blocks.0.resnets.1.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="128, 1, 1, 1" offset="601088" size="256" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="75" name="Constant_624607" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="68" name="self.encoder.down_blocks.0.resnets.1.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="76" name="__module.encoder.down_blocks.0.resnets.1.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="147,input.17">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="77" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_3" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="148,input.19">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="78" name="self.encoder.down_blocks.0.resnets.1.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="128, 128, 3, 3" offset="894736" size="294912" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.0.resnets.1.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -1436,11 +1198,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="79" name="self.encoder.down_blocks.0.resnets.1.conv2.weight" type="Convert" version="opset1">
+		<layer id="69" name="self.encoder.down_blocks.0.resnets.1.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>128</dim>
@@ -1458,7 +1217,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="80" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="70" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -1483,32 +1242,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="81" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="1189648" size="256" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="82" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="71" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 128, 1, 1" offset="601344" size="512" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>128</dim>
 					<dim>1</dim>
@@ -1516,7 +1253,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="83" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="72" name="__module.encoder.down_blocks.0.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -1533,7 +1270,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="156,hidden_states.3">
+				<port id="2" precision="FP32" names="111,hidden_states.3">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -1541,7 +1278,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="84" name="__module.encoder.down_blocks.0.resnets.1/aten::add/Add" type="Add" version="opset1">
+		<layer id="73" name="__module.encoder.down_blocks.0.resnets.1/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -1558,7 +1295,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="157,158,hidden_states.5">
+				<port id="2" precision="FP32" names="112,113,hidden_states.5">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -1566,10 +1303,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="85" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="128, 128, 3, 3" offset="1189904" size="294912" />
+		<layer id="74" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 128, 3, 3" offset="601856" size="147456" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.0.downsamplers.0.conv.weight">
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -1577,13 +1314,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="86" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="75" name="Convert_123750" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -1591,7 +1325,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -1599,124 +1333,118 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="87" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="1, 1" auto_pad="explicit" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>128</dim>
-					<dim>128</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
-			</input>
+		<layer id="76" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="128, 1, 1, 1" offset="749312" size="128" />
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="88" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="1484816" size="256" />
-			<output>
-				<port id="0" precision="FP16">
 					<dim>1</dim>
-					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="89" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="77" name="Convert_123753" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="90" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="78" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="168,input.21">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="91" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="256, 128, 1, 1" offset="1485072" size="65536" />
+		<layer id="79" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="128, 1, 1, 1" offset="749440" size="256" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight">
-					<dim>256</dim>
+				<port id="0" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="92" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="80" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>256</dim>
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="81" name="self.encoder.down_blocks.0.downsamplers.0.conv.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>128</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
 				<port id="1" precision="FP32">
-					<dim>256</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="93" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
+		<layer id="82" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -1725,195 +1453,183 @@
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>256</dim>
 					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>256</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="94" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="1550608" size="512" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="95" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="83" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 128, 1, 1" offset="749696" size="512" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
-					<dim>256</dim>
+					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="96" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="84" name="__module.encoder.down_blocks.0.downsamplers.0.conv/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>256</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>256</dim>
+					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="210,input_tensor.1">
+				<port id="2" precision="FP32" names="123,input.21">
 					<dim>-1</dim>
-					<dim>256</dim>
+					<dim>128</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="97" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="85" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 128, 1, 1" offset="750208" size="32768" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="98" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="86" name="Convert_123783" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
+					<dim>256</dim>
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="99" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="87" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 1, 1, 1" offset="782976" size="256" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="100" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="88" name="Convert_123786" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="101" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="89" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>256</dim>
 					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="2" precision="FP16">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="102" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
-				</port>
-			</input>
+		<layer id="90" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="256, 1, 1, 1" offset="783232" size="512" />
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="103" name="Constant_624608_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="1551120" size="256" />
-			<output>
+		<layer id="91" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
 				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>1</dim>
 					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>256</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="104" name="Constant_624608" type="Convert" version="opset1">
+		<layer id="92" name="self.encoder.down_blocks.1.resnets.0.conv_shortcut.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
+					<dim>256</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
@@ -1921,15 +1637,15 @@
 			</input>
 			<output>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
+					<dim>256</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="105" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="93" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -1938,7 +1654,7 @@
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
+					<dim>256</dim>
 					<dim>128</dim>
 					<dim>1</dim>
 					<dim>1</dim>
@@ -1947,71 +1663,66 @@
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>128</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="106" name="Constant_624609_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 128, 1, 1" offset="1551376" size="256" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="107" name="Constant_624609" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>128</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="94" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 256, 1, 1" offset="783744" size="1024" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
-					<dim>128</dim>
+					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="108" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/Add" type="Add" version="opset1">
+		<layer id="95" name="__module.encoder.down_blocks.1.resnets.0.conv_shortcut/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>128</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>128</dim>
+					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="183,input.23">
+				<port id="2" precision="FP32" names="165,input_tensor.1">
 					<dim>-1</dim>
-					<dim>128</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="109" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_4" type="Swish" version="opset4">
+		<layer id="96" name="self.encoder.down_blocks.1.resnets.0.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="784768" size="512" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.0.norm1.weight">
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="97" name="self.encoder.down_blocks.1.resnets.0.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="128" offset="785280" size="512" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.0.norm1.bias">
+					<dim>128</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="98" name="__module.encoder.down_blocks.1.resnets.0.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2019,9 +1730,15 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
+				<port id="1" precision="FP32">
+					<dim>128</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>128</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="184">
+				<port id="3" precision="FP32" names="138,input.23">
 					<dim>-1</dim>
 					<dim>128</dim>
 					<dim>-1</dim>
@@ -2029,32 +1746,28 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="110" name="self.encoder.down_blocks.1.resnets.0.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="256, 128, 3, 3" offset="1551632" size="589824" />
+		<layer id="99" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_4" type="Swish" version="opset4">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.1.resnets.0.conv1.weight">
-					<dim>256</dim>
+				<port id="1" precision="FP32" names="139">
+					<dim>-1</dim>
 					<dim>128</dim>
-					<dim>3</dim>
-					<dim>3</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="111" name="self.encoder.down_blocks.1.resnets.0.conv1.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>256</dim>
-					<dim>128</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
-			</input>
+		<layer id="100" name="self.encoder.down_blocks.1.resnets.0.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 128, 3, 3" offset="785792" size="294912" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -2062,16 +1775,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="112" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
+		<layer id="101" name="Convert_123651" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>128</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>128</dim>
 					<dim>3</dim>
@@ -2079,158 +1786,138 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="113" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="2141456" size="512" />
+		<layer id="102" name="self.encoder.down_blocks.1.resnets.0.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 1, 1, 1" offset="1080704" size="256" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="114" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="103" name="Convert_123654" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="115" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="104" name="self.encoder.down_blocks.1.resnets.0.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="191,input.25">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="116" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I32">
+					<dim>128</dim>
 					<dim>3</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="117" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
 					<dim>3</dim>
 				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
 			</output>
 		</layer>
-		<layer id="118" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="105" name="self.encoder.down_blocks.1.resnets.0.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="256, 1, 1, 1" offset="1080960" size="512" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="119" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="106" name="self.encoder.down_blocks.1.resnets.0.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="120" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="107" name="self.encoder.down_blocks.1.resnets.0.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="1" precision="FP32">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="121" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="108" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>128</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="1" precision="FP32">
+					<dim>256</dim>
+					<dim>128</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
@@ -2242,32 +1929,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="122" name="Constant_624610_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="2141968" size="512" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="123" name="Constant_624610" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="109" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 256, 1, 1" offset="1081472" size="1024" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>256</dim>
 					<dim>1</dim>
@@ -2275,7 +1940,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="124" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="110" name="__module.encoder.down_blocks.1.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2292,7 +1957,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="146,input.25">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -2300,41 +1965,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="125" name="Constant_624611_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="2142480" size="512" />
+		<layer id="111" name="self.encoder.down_blocks.1.resnets.0.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="1082496" size="1024" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.0.norm2.weight">
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="126" name="Constant_624611" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="112" name="self.encoder.down_blocks.1.resnets.0.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="1083520" size="1024" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.0.norm2.bias">
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="127" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="113" name="__module.encoder.down_blocks.1.resnets.0.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2343,14 +1991,14 @@
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>256</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="194,input.27">
+				<port id="3" precision="FP32" names="149,input.27">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -2358,7 +2006,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="128" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_5" type="Swish" version="opset4">
+		<layer id="114" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_5" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2368,7 +2016,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="195,input.29">
+				<port id="1" precision="FP32" names="150,input.29">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -2376,10 +2024,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="129" name="self.encoder.down_blocks.1.resnets.0.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="256, 256, 3, 3" offset="2142992" size="1179648" />
+		<layer id="115" name="self.encoder.down_blocks.1.resnets.0.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 256, 3, 3" offset="1084544" size="589824" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.1.resnets.0.conv2.weight">
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -2387,13 +2035,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="130" name="self.encoder.down_blocks.1.resnets.0.conv2.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="116" name="Convert_123607" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -2401,7 +2046,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -2409,127 +2054,118 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="131" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>256</dim>
-					<dim>256</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
-			</input>
+		<layer id="117" name="self.encoder.down_blocks.1.resnets.0.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 1, 1, 1" offset="1674368" size="256" />
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="132" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="3322640" size="512" />
-			<output>
-				<port id="0" precision="FP16">
 					<dim>1</dim>
-					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="133" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="118" name="Convert_123610" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="134" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="119" name="self.encoder.down_blocks.1.resnets.0.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="203,hidden_states.9">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="135" name="__module.encoder.down_blocks.1.resnets.0/aten::add/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+		<layer id="120" name="self.encoder.down_blocks.1.resnets.0.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="256, 1, 1, 1" offset="1674624" size="512" />
+			<output>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
+			</output>
+		</layer>
+		<layer id="121" name="self.encoder.down_blocks.1.resnets.0.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="211,212,input.31">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="136" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="122" name="self.encoder.down_blocks.1.resnets.0.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="137" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="123" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2537,48 +2173,60 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</input>
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>256</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="138" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="124" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 256, 1, 1" offset="1675136" size="1024" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>256</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="139" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="125" name="__module.encoder.down_blocks.1.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>256</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>256</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="158,hidden_states.9">
+					<dim>-1</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="140" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="126" name="__module.encoder.down_blocks.1.resnets.0/aten::add/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2586,27 +2234,15 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
-			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="141" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="166,167,input.31">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -2614,41 +2250,48 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="142" name="Constant_624612_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="3323152" size="512" />
+		<layer id="127" name="self.encoder.down_blocks.1.resnets.1.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="1676160" size="1024" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.1.norm1.weight">
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="143" name="Constant_624612" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="128" name="self.encoder.down_blocks.1.resnets.1.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="1677184" size="1024" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.1.norm1.bias">
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="129" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>256</dim>
+				</port>
+				<port id="2" precision="FP32">
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="3" precision="FP32" names="175,input.33">
+					<dim>-1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="144" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="130" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_6" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2656,15 +2299,9 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="1" precision="FP32" names="176">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -2672,86 +2309,120 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="145" name="Constant_624613_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="3323664" size="512" />
+		<layer id="131" name="self.encoder.down_blocks.1.resnets.1.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 256, 3, 3" offset="1678208" size="589824" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="132" name="Convert_123618" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="133" name="self.encoder.down_blocks.1.resnets.1.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 1, 1, 1" offset="2268032" size="256" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="146" name="Constant_624613" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="134" name="Convert_123621" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="147" name="__module.encoder.down_blocks.1.resnets.1.norm1/aten::group_norm/Add" type="Add" version="opset1">
+		<layer id="135" name="self.encoder.down_blocks.1.resnets.1.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="220,input.33">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="148" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_6" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
+		<layer id="136" name="self.encoder.down_blocks.1.resnets.1.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="256, 1, 1, 1" offset="2268288" size="512" />
 			<output>
-				<port id="1" precision="FP32" names="221">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="149" name="self.encoder.down_blocks.1.resnets.1.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="256, 256, 3, 3" offset="3324176" size="1179648" />
+		<layer id="137" name="self.encoder.down_blocks.1.resnets.1.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.1.resnets.1.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -2759,11 +2430,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="150" name="self.encoder.down_blocks.1.resnets.1.conv1.weight" type="Convert" version="opset1">
+		<layer id="138" name="self.encoder.down_blocks.1.resnets.1.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>256</dim>
@@ -2781,7 +2449,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="151" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="139" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2806,32 +2474,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="152" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="4503824" size="512" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="153" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="140" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 256, 1, 1" offset="2268800" size="1024" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>256</dim>
 					<dim>1</dim>
@@ -2839,7 +2485,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="154" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="141" name="__module.encoder.down_blocks.1.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -2856,7 +2502,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="228,input.35">
+				<port id="2" precision="FP32" names="183,input.35">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -2864,19 +2510,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="155" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="142" name="self.encoder.down_blocks.1.resnets.1.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="2269824" size="1024" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.1.norm2.weight">
+					<dim>256</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="156" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="143" name="self.encoder.down_blocks.1.resnets.1.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="2270848" size="1024" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.1.resnets.1.norm2.bias">
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="144" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -2884,221 +2535,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>256</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>256</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="186,input.37">
+					<dim>-1</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="157" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="158" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="145" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_7" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>256</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="159" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="187,input.39">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="146" name="self.encoder.down_blocks.1.resnets.1.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 256, 3, 3" offset="2271872" size="589824" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="160" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="147" name="Convert_123629" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="161" name="Constant_624614_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="4504336" size="512" />
+		<layer id="148" name="self.encoder.down_blocks.1.resnets.1.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 1, 1, 1" offset="2861696" size="256" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="162" name="Constant_624614" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="149" name="Convert_123632" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="163" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="150" name="self.encoder.down_blocks.1.resnets.1.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="164" name="Constant_624615_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="4504848" size="512" />
+		<layer id="151" name="self.encoder.down_blocks.1.resnets.1.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="256, 1, 1, 1" offset="2861952" size="512" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="165" name="Constant_624615" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="152" name="self.encoder.down_blocks.1.resnets.1.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="166" name="__module.encoder.down_blocks.1.resnets.1.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="231,input.37">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="167" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_7" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="232,input.39">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="168" name="self.encoder.down_blocks.1.resnets.1.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="256, 256, 3, 3" offset="4505360" size="1179648" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.1.resnets.1.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3106,11 +2690,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="169" name="self.encoder.down_blocks.1.resnets.1.conv2.weight" type="Convert" version="opset1">
+		<layer id="153" name="self.encoder.down_blocks.1.resnets.1.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>256</dim>
@@ -3128,7 +2709,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="170" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="154" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3153,32 +2734,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="171" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="5685008" size="512" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="172" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="155" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 256, 1, 1" offset="2862464" size="1024" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>256</dim>
 					<dim>1</dim>
@@ -3186,7 +2745,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="173" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="156" name="__module.encoder.down_blocks.1.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3203,7 +2762,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="240,hidden_states.11">
+				<port id="2" precision="FP32" names="195,hidden_states.11">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -3211,7 +2770,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="174" name="__module.encoder.down_blocks.1.resnets.1/aten::add/Add" type="Add" version="opset1">
+		<layer id="157" name="__module.encoder.down_blocks.1.resnets.1/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -3228,7 +2787,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="241,242,hidden_states.13">
+				<port id="2" precision="FP32" names="196,197,hidden_states.13">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -3236,10 +2795,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="175" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="256, 256, 3, 3" offset="5685520" size="1179648" />
+		<layer id="158" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 256, 3, 3" offset="2863488" size="589824" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.1.downsamplers.0.conv.weight">
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3247,13 +2806,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="176" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="159" name="Convert_123640" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3261,7 +2817,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3269,66 +2825,118 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="177" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="1, 1" auto_pad="explicit" />
+		<layer id="160" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="256, 1, 1, 1" offset="3453312" size="256" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="161" name="Convert_123643" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="162" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
 					<dim>256</dim>
 					<dim>256</dim>
 					<dim>3</dim>
 					<dim>3</dim>
 				</port>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="178" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="6865168" size="512" />
+		<layer id="163" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="256, 1, 1, 1" offset="3453568" size="512" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="179" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="164" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>256</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="165" name="self.encoder.down_blocks.1.downsamplers.0.conv.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>256</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
 			<output>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="180" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="166" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3337,14 +2945,14 @@
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="252,input.41">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -3352,41 +2960,19 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="181" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 256, 1, 1" offset="6865680" size="262144" />
+		<layer id="167" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 256, 1, 1" offset="3454080" size="1024" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight">
-					<dim>512</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="182" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>512</dim>
-					<dim>256</dim>
-					<dim>1</dim>
+				<port id="0" precision="FP32">
 					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>512</dim>
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="183" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
+		<layer id="168" name="__module.encoder.down_blocks.1.downsamplers.0.conv/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3395,269 +2981,240 @@
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>512</dim>
+					<dim>1</dim>
 					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="207,input.41">
 					<dim>-1</dim>
-					<dim>512</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="184" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="7127824" size="1024" />
+		<layer id="169" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 256, 1, 1" offset="3455104" size="131072" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
+					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="185" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="170" name="Convert_123761" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
+					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
+					<dim>256</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="186" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+		<layer id="171" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="3586176" size="512" />
+			<output>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="172" name="Convert_123764" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="294,input_tensor">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="187" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="188" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="173" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="189" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="174" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="3586688" size="1024" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="190" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="175" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="191" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="176" name="self.encoder.down_blocks.2.resnets.0.conv_shortcut.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
 					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="192" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="177" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>256</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>256</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="193" name="Constant_624616_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="7128848" size="512" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="194" name="Constant_624616" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="178" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="3587712" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
-					<dim>256</dim>
+					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="195" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="179" name="__module.encoder.down_blocks.2.resnets.0.conv_shortcut/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>256</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>256</dim>
+					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="249,input_tensor">
 					<dim>-1</dim>
-					<dim>256</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="196" name="Constant_624617_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 256, 1, 1" offset="7129360" size="512" />
+		<layer id="180" name="self.encoder.down_blocks.2.resnets.0.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="3589760" size="1024" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.0.norm1.weight">
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="197" name="Constant_624617" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="181" name="self.encoder.down_blocks.2.resnets.0.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="256" offset="3590784" size="1024" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.0.norm1.bias">
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="198" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="182" name="__module.encoder.down_blocks.2.resnets.0.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3666,14 +3223,14 @@
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>256</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>256</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="267,input.43">
+				<port id="3" precision="FP32" names="222,input.43">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -3681,7 +3238,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="199" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_8" type="Swish" version="opset4">
+		<layer id="183" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_8" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3691,7 +3248,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="268">
+				<port id="1" precision="FP32" names="223">
 					<dim>-1</dim>
 					<dim>256</dim>
 					<dim>-1</dim>
@@ -3699,10 +3256,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="200" name="self.encoder.down_blocks.2.resnets.0.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 256, 3, 3" offset="7129872" size="2359296" />
+		<layer id="184" name="self.encoder.down_blocks.2.resnets.0.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 256, 3, 3" offset="3591808" size="1179648" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.2.resnets.0.conv1.weight">
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3710,13 +3267,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="201" name="self.encoder.down_blocks.2.resnets.0.conv1.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="185" name="Convert_123596" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3724,7 +3278,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>256</dim>
 					<dim>3</dim>
@@ -3732,151 +3286,195 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="202" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>256</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>512</dim>
-					<dim>256</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
-			</input>
+		<layer id="186" name="self.encoder.down_blocks.2.resnets.0.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="4771456" size="512" />
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="203" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="9489168" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
+		<layer id="187" name="Convert_123599" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="204" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="188" name="self.encoder.down_blocks.2.resnets.0.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="189" name="self.encoder.down_blocks.2.resnets.0.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="4771968" size="1024" />
+			<output>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="205" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="190" name="self.encoder.down_blocks.2.resnets.0.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="275,input.45">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="206" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="191" name="self.encoder.down_blocks.2.resnets.0.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="207" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="192" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>512</dim>
+					<dim>256</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>256</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</input>
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="208" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="193" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="4772992" size="2048" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="209" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="194" name="__module.encoder.down_blocks.2.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="230,input.45">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="210" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="195" name="self.encoder.down_blocks.2.resnets.0.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="4775040" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.0.norm2.weight">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="196" name="self.encoder.down_blocks.2.resnets.0.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="4777088" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.0.norm2.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="197" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -3884,27 +3482,33 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="3" precision="FP32" names="233,input.47">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="211" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="198" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_9" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="1" precision="FP32" names="234,input.49">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -3912,144 +3516,120 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="212" name="Constant_624618_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="9490192" size="1024" />
+		<layer id="199" name="self.encoder.down_blocks.2.resnets.0.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="4779136" size="2359296" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="213" name="Constant_624618" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="214" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="200" name="Convert_123464" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="215" name="Constant_624619_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="9491216" size="1024" />
+		<layer id="201" name="self.encoder.down_blocks.2.resnets.0.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="7138432" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="216" name="Constant_624619" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="202" name="Convert_123467" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="217" name="__module.encoder.down_blocks.2.resnets.0.norm2/aten::group_norm/Add" type="Add" version="opset1">
+		<layer id="203" name="self.encoder.down_blocks.2.resnets.0.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="278,input.47">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="218" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_9" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
+		<layer id="204" name="self.encoder.down_blocks.2.resnets.0.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="7138944" size="1024" />
 			<output>
-				<port id="1" precision="FP32" names="279,input.49">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="219" name="self.encoder.down_blocks.2.resnets.0.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="9492240" size="4718592" />
+		<layer id="205" name="self.encoder.down_blocks.2.resnets.0.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.2.resnets.0.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -4057,11 +3637,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="220" name="self.encoder.down_blocks.2.resnets.0.conv2.weight" type="Convert" version="opset1">
+		<layer id="206" name="self.encoder.down_blocks.2.resnets.0.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -4079,7 +3656,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="221" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="207" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4104,32 +3681,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="222" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="14210832" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="223" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="208" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="7139968" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -4137,7 +3692,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="224" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="209" name="__module.encoder.down_blocks.2.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4154,7 +3709,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="287,hidden_states.17">
+				<port id="2" precision="FP32" names="242,hidden_states.17">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -4162,7 +3717,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="225" name="__module.encoder.down_blocks.2.resnets.0/aten::add/Add" type="Add" version="opset1">
+		<layer id="210" name="__module.encoder.down_blocks.2.resnets.0/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4179,7 +3734,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="295,296,input.51">
+				<port id="2" precision="FP32" names="250,251,input.51">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -4187,19 +3742,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="226" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="211" name="self.encoder.down_blocks.2.resnets.1.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="7142016" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.1.norm1.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="227" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="212" name="self.encoder.down_blocks.2.resnets.1.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="7144064" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.1.norm1.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="213" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -4207,221 +3767,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="259,input.53">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="228" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="229" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="214" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_10" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="230" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="260">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="215" name="self.encoder.down_blocks.2.resnets.1.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="7146112" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="231" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="216" name="Convert_123475" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="232" name="Constant_624620_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="14211856" size="1024" />
+		<layer id="217" name="self.encoder.down_blocks.2.resnets.1.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="9505408" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="233" name="Constant_624620" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="218" name="Convert_123478" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="234" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="219" name="self.encoder.down_blocks.2.resnets.1.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="235" name="Constant_624621_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="14212880" size="1024" />
+		<layer id="220" name="self.encoder.down_blocks.2.resnets.1.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="9505920" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="236" name="Constant_624621" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="221" name="self.encoder.down_blocks.2.resnets.1.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="237" name="__module.encoder.down_blocks.2.resnets.1.norm1/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="304,input.53">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="238" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_10" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="305">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="239" name="self.encoder.down_blocks.2.resnets.1.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="14213904" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.2.resnets.1.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -4429,11 +3922,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="240" name="self.encoder.down_blocks.2.resnets.1.conv1.weight" type="Convert" version="opset1">
+		<layer id="222" name="self.encoder.down_blocks.2.resnets.1.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -4451,7 +3941,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="241" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="223" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4476,32 +3966,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="242" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="18932496" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="243" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="224" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="9506944" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -4509,7 +3977,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="244" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="225" name="__module.encoder.down_blocks.2.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4526,7 +3994,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="312,input.55">
+				<port id="2" precision="FP32" names="267,input.55">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -4534,19 +4002,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="245" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="226" name="self.encoder.down_blocks.2.resnets.1.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="9508992" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.1.norm2.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="246" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="227" name="self.encoder.down_blocks.2.resnets.1.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="9511040" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.2.resnets.1.norm2.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="228" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -4554,221 +4027,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="270,input.57">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="247" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="248" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="229" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_11" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="249" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="271,input.59">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="230" name="self.encoder.down_blocks.2.resnets.1.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="9513088" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="250" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="231" name="Convert_123486" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="251" name="Constant_624622_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="18933520" size="1024" />
+		<layer id="232" name="self.encoder.down_blocks.2.resnets.1.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="11872384" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="252" name="Constant_624622" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="233" name="Convert_123489" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="253" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="234" name="self.encoder.down_blocks.2.resnets.1.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="254" name="Constant_624623_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="18934544" size="1024" />
+		<layer id="235" name="self.encoder.down_blocks.2.resnets.1.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="11872896" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="255" name="Constant_624623" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="236" name="self.encoder.down_blocks.2.resnets.1.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="256" name="__module.encoder.down_blocks.2.resnets.1.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="315,input.57">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="257" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_11" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="316,input.59">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="258" name="self.encoder.down_blocks.2.resnets.1.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="18935568" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.2.resnets.1.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -4776,11 +4182,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="259" name="self.encoder.down_blocks.2.resnets.1.conv2.weight" type="Convert" version="opset1">
+		<layer id="237" name="self.encoder.down_blocks.2.resnets.1.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -4798,7 +4201,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="260" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="238" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4823,32 +4226,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="261" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="23654160" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="262" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="239" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="11873920" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -4856,7 +4237,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="263" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="240" name="__module.encoder.down_blocks.2.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4873,7 +4254,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="324,hidden_states.19">
+				<port id="2" precision="FP32" names="279,hidden_states.19">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -4881,7 +4262,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="264" name="__module.encoder.down_blocks.2.resnets.1/aten::add/Add" type="Add" version="opset1">
+		<layer id="241" name="__module.encoder.down_blocks.2.resnets.1/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -4898,7 +4279,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="325,326,hidden_states.21">
+				<port id="2" precision="FP32" names="280,281,hidden_states.21">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -4906,10 +4287,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="265" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="23655184" size="4718592" />
+		<layer id="242" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="11875968" size="2359296" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.2.downsamplers.0.conv.weight">
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -4917,13 +4298,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="266" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="243" name="Convert_123497" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -4931,7 +4309,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -4939,102 +4317,118 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="267" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="1, 1" auto_pad="explicit" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+		<layer id="244" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="14235264" size="512" />
+			<output>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>512</dim>
+			</output>
+		</layer>
+		<layer id="245" name="Convert_123500" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="268" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="28373776" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="269" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="246" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="247" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="14235776" size="1024" />
+			<output>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="270" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="248" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight/fq_weights_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="336,input.61">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="271" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="249" name="self.encoder.down_blocks.2.downsamplers.0.conv.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="272" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="250" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5042,48 +4436,76 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
 					<dim>3</dim>
 				</port>
 			</input>
 			<output>
 				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="273" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="251" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="14236800" size="2048" />
 			<output>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="274" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="252" name="__module.encoder.down_blocks.2.downsamplers.0.conv/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="291,input.61">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="275" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
+		<layer id="253" name="self.encoder.down_blocks.3.resnets.0.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="14238848" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.0.norm1.weight">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="254" name="self.encoder.down_blocks.3.resnets.0.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="14240896" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.0.norm1.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="255" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5091,27 +4513,33 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
+				</port>
 			</input>
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="3" precision="FP32" names="303,input.63">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="276" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="256" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_12" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="1" precision="FP32" names="304">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -5119,144 +4547,120 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="277" name="Constant_624624_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="28374800" size="1024" />
+		<layer id="257" name="self.encoder.down_blocks.3.resnets.0.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="14242944" size="2359296" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="278" name="Constant_624624" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="279" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="258" name="Convert_123508" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="280" name="Constant_624625_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="28375824" size="1024" />
+		<layer id="259" name="self.encoder.down_blocks.3.resnets.0.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="16602240" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="281" name="Constant_624625" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="260" name="Convert_123511" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="282" name="__module.encoder.down_blocks.3.resnets.0.norm1/aten::group_norm/Add" type="Add" version="opset1">
+		<layer id="261" name="self.encoder.down_blocks.3.resnets.0.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="348,input.63">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="283" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_12" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
+		<layer id="262" name="self.encoder.down_blocks.3.resnets.0.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="16602752" size="1024" />
 			<output>
-				<port id="1" precision="FP32" names="349">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="284" name="self.encoder.down_blocks.3.resnets.0.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="28376848" size="4718592" />
+		<layer id="263" name="self.encoder.down_blocks.3.resnets.0.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.3.resnets.0.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -5264,11 +4668,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="285" name="self.encoder.down_blocks.3.resnets.0.conv1.weight" type="Convert" version="opset1">
+		<layer id="264" name="self.encoder.down_blocks.3.resnets.0.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -5286,7 +4687,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="286" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="265" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5311,32 +4712,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="287" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="33095440" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="288" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="266" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="16603776" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -5344,7 +4723,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="289" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="267" name="__module.encoder.down_blocks.3.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5361,7 +4740,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="356,input.65">
+				<port id="2" precision="FP32" names="311,input.65">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -5369,19 +4748,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="290" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="268" name="self.encoder.down_blocks.3.resnets.0.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="16605824" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.0.norm2.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="291" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="269" name="self.encoder.down_blocks.3.resnets.0.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="16607872" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.0.norm2.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="270" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5389,221 +4773,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="314,input.67">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="292" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="293" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="271" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_13" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="294" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="315,input.69">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="272" name="self.encoder.down_blocks.3.resnets.0.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="16609920" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="295" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="273" name="Convert_123519" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="296" name="Constant_624626_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="33096464" size="1024" />
+		<layer id="274" name="self.encoder.down_blocks.3.resnets.0.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="18969216" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="297" name="Constant_624626" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="275" name="Convert_123522" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="298" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="276" name="self.encoder.down_blocks.3.resnets.0.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="299" name="Constant_624627_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="33097488" size="1024" />
+		<layer id="277" name="self.encoder.down_blocks.3.resnets.0.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="18969728" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="300" name="Constant_624627" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="278" name="self.encoder.down_blocks.3.resnets.0.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="301" name="__module.encoder.down_blocks.3.resnets.0.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="359,input.67">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="302" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_13" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="360,input.69">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="303" name="self.encoder.down_blocks.3.resnets.0.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="33098512" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.3.resnets.0.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -5611,11 +4928,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="304" name="self.encoder.down_blocks.3.resnets.0.conv2.weight" type="Convert" version="opset1">
+		<layer id="279" name="self.encoder.down_blocks.3.resnets.0.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -5633,7 +4947,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="305" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="280" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5658,32 +4972,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="306" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="37817104" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="307" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="281" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="18970752" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -5691,7 +4983,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="308" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="282" name="__module.encoder.down_blocks.3.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5708,7 +5000,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="368,hidden_states.25">
+				<port id="2" precision="FP32" names="323,hidden_states.25">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -5716,7 +5008,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="309" name="__module.encoder.down_blocks.3.resnets.0/aten::add/Add" type="Add" version="opset1">
+		<layer id="283" name="__module.encoder.down_blocks.3.resnets.0/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -5733,7 +5025,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="369,370,input.71">
+				<port id="2" precision="FP32" names="324,325,input.71">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -5741,19 +5033,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="310" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="284" name="self.encoder.down_blocks.3.resnets.1.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="18972800" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.1.norm1.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="311" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="285" name="self.encoder.down_blocks.3.resnets.1.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="18974848" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.1.norm1.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="286" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -5761,221 +5058,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="333,input.73">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="312" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="313" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="287" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_14" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="314" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="334">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="288" name="self.encoder.down_blocks.3.resnets.1.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="18976896" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="315" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="289" name="Convert_123530" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="316" name="Constant_624628_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="37818128" size="1024" />
+		<layer id="290" name="self.encoder.down_blocks.3.resnets.1.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="21336192" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="317" name="Constant_624628" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="291" name="Convert_123533" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="318" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="292" name="self.encoder.down_blocks.3.resnets.1.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="319" name="Constant_624629_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="37819152" size="1024" />
+		<layer id="293" name="self.encoder.down_blocks.3.resnets.1.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="21336704" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="320" name="Constant_624629" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="294" name="self.encoder.down_blocks.3.resnets.1.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="321" name="__module.encoder.down_blocks.3.resnets.1.norm1/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="378,input.73">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="322" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_14" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="379">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="323" name="self.encoder.down_blocks.3.resnets.1.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="37820176" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.3.resnets.1.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -5983,11 +5213,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="324" name="self.encoder.down_blocks.3.resnets.1.conv1.weight" type="Convert" version="opset1">
+		<layer id="295" name="self.encoder.down_blocks.3.resnets.1.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -6005,7 +5232,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="325" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="296" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6030,32 +5257,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="326" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="42538768" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="327" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="297" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="21337728" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -6063,7 +5268,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="328" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="298" name="__module.encoder.down_blocks.3.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6080,7 +5285,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="386,input.75">
+				<port id="2" precision="FP32" names="341,input.75">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -6088,19 +5293,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="329" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="299" name="self.encoder.down_blocks.3.resnets.1.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="21339776" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.1.norm2.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="330" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="300" name="self.encoder.down_blocks.3.resnets.1.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="21341824" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.down_blocks.3.resnets.1.norm2.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="301" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -6108,221 +5318,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="344,input.77">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="331" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="332" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="302" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_15" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="333" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="345,input.79">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="303" name="self.encoder.down_blocks.3.resnets.1.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="21343872" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="334" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="304" name="Convert_123541" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="335" name="Constant_624630_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="42539792" size="1024" />
+		<layer id="305" name="self.encoder.down_blocks.3.resnets.1.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="23703168" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="336" name="Constant_624630" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="306" name="Convert_123544" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="337" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="307" name="self.encoder.down_blocks.3.resnets.1.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="338" name="Constant_624631_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="42540816" size="1024" />
+		<layer id="308" name="self.encoder.down_blocks.3.resnets.1.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="23703680" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="339" name="Constant_624631" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="309" name="self.encoder.down_blocks.3.resnets.1.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="340" name="__module.encoder.down_blocks.3.resnets.1.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="389,input.77">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="341" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_15" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="390,input.79">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="342" name="self.encoder.down_blocks.3.resnets.1.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="42541840" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.down_blocks.3.resnets.1.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -6330,11 +5473,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="343" name="self.encoder.down_blocks.3.resnets.1.conv2.weight" type="Convert" version="opset1">
+		<layer id="310" name="self.encoder.down_blocks.3.resnets.1.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -6352,7 +5492,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="344" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="311" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6377,32 +5517,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="345" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="47260432" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="346" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="312" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="23704704" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -6410,7 +5528,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="347" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="313" name="__module.encoder.down_blocks.3.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6427,7 +5545,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="398,hidden_states.27">
+				<port id="2" precision="FP32" names="353,hidden_states.27">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -6435,7 +5553,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="348" name="__module.encoder.down_blocks.3.resnets.1/aten::add/Add" type="Add" version="opset1">
+		<layer id="314" name="__module.encoder.down_blocks.3.resnets.1/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6452,7 +5570,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="399,400,input.81">
+				<port id="2" precision="FP32" names="354,355,input.81">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -6460,19 +5578,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="349" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="315" name="self.encoder.mid_block.resnets.0.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="23706752" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.0.norm1.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="350" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="316" name="self.encoder.mid_block.resnets.0.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="23708800" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.0.norm1.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="317" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -6480,221 +5603,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="369,input.83">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="351" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="352" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="318" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_16" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="353" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="370">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="319" name="self.encoder.mid_block.resnets.0.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="23710848" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="354" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="320" name="Convert_123552" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="355" name="Constant_624632_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="47261456" size="1024" />
+		<layer id="321" name="self.encoder.mid_block.resnets.0.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="26070144" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="356" name="Constant_624632" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="322" name="Convert_123555" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="357" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="323" name="self.encoder.mid_block.resnets.0.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="358" name="Constant_624633_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="47262480" size="1024" />
+		<layer id="324" name="self.encoder.mid_block.resnets.0.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="26070656" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="359" name="Constant_624633" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="325" name="self.encoder.mid_block.resnets.0.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="360" name="__module.encoder.mid_block.resnets.0.norm1/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="414,input.83">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="361" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_16" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="415">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="362" name="self.encoder.mid_block.resnets.0.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="47263504" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.resnets.0.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -6702,11 +5758,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="363" name="self.encoder.mid_block.resnets.0.conv1.weight" type="Convert" version="opset1">
+		<layer id="326" name="self.encoder.mid_block.resnets.0.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -6724,7 +5777,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="364" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="327" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6749,32 +5802,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="365" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="51982096" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="366" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="328" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="26071680" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -6782,7 +5813,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="367" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="329" name="__module.encoder.mid_block.resnets.0.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -6799,7 +5830,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="422,input.85">
+				<port id="2" precision="FP32" names="377,input.85">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -6807,19 +5838,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="368" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="330" name="self.encoder.mid_block.resnets.0.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="26073728" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.0.norm2.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="369" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="331" name="self.encoder.mid_block.resnets.0.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="26075776" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.0.norm2.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="332" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -6827,235 +5863,165 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="380,input.87">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="370" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="371" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="333" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_17" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="372" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="381,input.89">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="334" name="self.encoder.mid_block.resnets.0.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="26077824" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="373" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="335" name="Convert_123563" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="374" name="Constant_624634_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="51983120" size="1024" />
+		<layer id="336" name="self.encoder.mid_block.resnets.0.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="28437120" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="375" name="Constant_624634" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="337" name="Convert_123566" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="376" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="338" name="self.encoder.mid_block.resnets.0.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="377" name="Constant_624635_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="51984144" size="1024" />
+		<layer id="339" name="self.encoder.mid_block.resnets.0.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="28437632" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="378" name="Constant_624635" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="340" name="self.encoder.mid_block.resnets.0.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="379" name="__module.encoder.mid_block.resnets.0.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="341" name="self.encoder.mid_block.resnets.0.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="425,input.87">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="380" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_17" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="426,input.89">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="381" name="self.encoder.mid_block.resnets.0.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="51985168" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.resnets.0.conv2.weight">
-					<dim>512</dim>
-					<dim>512</dim>
-					<dim>3</dim>
-					<dim>3</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="382" name="self.encoder.mid_block.resnets.0.conv2.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -7071,7 +6037,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="383" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="342" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -7096,32 +6062,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="384" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="56703760" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="385" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="343" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="28438656" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -7129,7 +6073,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="386" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="344" name="__module.encoder.mid_block.resnets.0.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -7146,7 +6090,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="434,hidden_states.29">
+				<port id="2" precision="FP32" names="389,hidden_states.29">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -7154,7 +6098,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="387" name="__module.encoder.mid_block.resnets.0/aten::add/Add" type="Add" version="opset1">
+		<layer id="345" name="__module.encoder.mid_block.resnets.0/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -7171,7 +6115,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="435,436,hidden_states.31">
+				<port id="2" precision="FP32" names="390,391,hidden_states.31">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -7179,8 +6123,16 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="388" name="__module.encoder.mid_block.attentions.0/aten::size/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
+		<layer id="346" name="Constant_95425" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="28440704" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="347" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -7188,461 +6140,430 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
-			<output>
 				<port id="1" precision="I64">
-					<dim>4</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="389" name="Constant_624241" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704784" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+			</input>
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="407">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="390" name="__module.encoder.mid_block.attentions.0/aten::size/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="348" name="__module.encoder.mid_block.attentions.0/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="28440728" size="12" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="I32">
+					<dim>3</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="391" name="__module.encoder.mid_block.attentions.0/aten::size/Gather" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="349" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose" type="Transpose" version="opset1">
 			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="1" precision="I32">
+					<dim>3</dim>
 				</port>
-				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="3" precision="I64" names="443">
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="408,hidden_states.33">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="392" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_0" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704796" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="350" name="__module.encoder.mid_block.attentions.0/aten::transpose/Constant_1" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="28440728" size="12" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="I32">
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="393" name="67" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="56704804" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64" names="67" />
-			</output>
-		</layer>
-		<layer id="394" name="__module.encoder.mid_block.attentions.0/aten::size/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="395" name="__module.encoder.mid_block.attentions.0/aten::size/Gather_2" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="351" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_1" type="Transpose" version="opset1">
 			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="3" precision="I64" names="445" />
+				<port id="2" precision="FP32" names="410,input.91">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="396" name="62" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="56704812" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="352" name="self.encoder.mid_block.attentions.0.group_norm.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="28440740" size="2048" />
 			<output>
-				<port id="0" precision="I64" names="62" />
+				<port id="0" precision="FP32" names="self.encoder.mid_block.attentions.0.group_norm.weight">
+					<dim>512</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="397" name="__module.encoder.mid_block.attentions.0/aten::size/Constant_2" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="353" name="self.encoder.mid_block.attentions.0.group_norm.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="28442788" size="2048" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="FP32" names="self.encoder.mid_block.attentions.0.group_norm.bias">
+					<dim>512</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="398" name="__module.encoder.mid_block.attentions.0/aten::size/Gather_3" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="354" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="3" precision="I64" names="447" />
+				<port id="3" precision="FP32" names="413">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="399" name="__module.encoder.mid_block.attentions.0/aten::mul/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="355" name="self.encoder.mid_block.attentions.0.to_q.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512" offset="28444836" size="262144" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="356" name="Convert_123684" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64" />
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
 			</input>
 			<output>
-				<port id="2" precision="I64" names="449,450" />
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="400" name="Constant_764435" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704820" size="8" />
+		<layer id="357" name="self.encoder.mid_block.attentions.0.to_q.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1" offset="28706980" size="512" />
 			<output>
-				<port id="0" precision="I64">
+				<port id="0" precision="U8">
+					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="401" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="358" name="Convert_123687" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64">
+				<port id="0" precision="U8">
+					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I64">
+				<port id="1" precision="FP16">
+					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="402" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Concat" type="Concat" version="opset1">
-			<data axis="0" />
+		<layer id="359" name="self.encoder.mid_block.attentions.0.to_q.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
-				<port id="2" precision="I64">
+				<port id="1" precision="FP16">
+					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="3" precision="I64" names="451">
-					<dim>3</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="403" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="360" name="self.encoder.mid_block.attentions.0.to_q.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1" offset="28707492" size="1024" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="361" name="self.encoder.mid_block.attentions.0.to_q.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>3</dim>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="452">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="404" name="__module.encoder.mid_block.attentions.0/aten::transpose/ScatterElementsUpdate" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="56704828" size="12" />
+		<layer id="362" name="self.encoder.mid_block.attentions.0.to_q.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="405" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose" type="Transpose" version="opset1">
+		<layer id="363" name="__module.encoder.mid_block.attentions.0.to_q/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="true" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="453,hidden_states.33">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="406" name="__module.encoder.mid_block.attentions.0/aten::transpose/ScatterElementsUpdate_1" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="56704828" size="12" />
+		<layer id="364" name="Constant_95310" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="28708516" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="407" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_1" type="Transpose" version="opset1">
+		<layer id="365" name="__module.encoder.mid_block.attentions.0.to_q/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="455,input.91">
+				<port id="2" precision="FP32" names="417,query">
 					<dim>-1</dim>
-					<dim>512</dim>
 					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="408" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="366" name="Constant_95426" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="28710564" size="32" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="409" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/Reshape" type="Reshape" version="opset1">
+		<layer id="367" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape_1" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>512</dim>
 					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="431">
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="410" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
+		<layer id="368" name="Constant_95255" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="28710596" size="32" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
+				<port id="0" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="411" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="369" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_3" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
 					<dim>1</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="2" precision="FP32" names="432">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>1</dim>
 					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="412" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
+		<layer id="370" name="self.encoder.mid_block.attentions.0.to_k.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512" offset="28710628" size="262144" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="413" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="371" name="Convert_123673" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="414" name="Constant_624636_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1" offset="56704840" size="1024" />
+		<layer id="372" name="self.encoder.mid_block.attentions.0.to_k.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1" offset="28972772" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="415" name="Constant_624636" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="373" name="Convert_123676" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="416" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="374" name="self.encoder.mid_block.attentions.0.to_k.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="417" name="Constant_624637_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1" offset="56705864" size="1024" />
+		<layer id="375" name="self.encoder.mid_block.attentions.0.to_k.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1" offset="28973284" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="418" name="Constant_624637" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="376" name="self.encoder.mid_block.attentions.0.to_k.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="419" name="__module.encoder.mid_block.attentions.0.group_norm/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="458">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="420" name="self.encoder.mid_block.attentions.0.to_q.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512" offset="56706888" size="524288" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.attentions.0.to_q.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="421" name="self.encoder.mid_block.attentions.0.to_q.weight" type="Convert" version="opset1">
+		<layer id="377" name="self.encoder.mid_block.attentions.0.to_k.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -7656,7 +6577,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="422" name="__module.encoder.mid_block.attentions.0.to_q/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="378" name="__module.encoder.mid_block.attentions.0.to_k/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="true" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -7677,37 +6598,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="423" name="Constant_624638_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 512" offset="57231176" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="424" name="Constant_624638" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</input>
+		<layer id="379" name="Constant_95311" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="28974308" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="425" name="__module.encoder.mid_block.attentions.0.to_q/aten::linear/Add" type="Add" version="opset1">
+		<layer id="380" name="__module.encoder.mid_block.attentions.0.to_k/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -7722,278 +6623,245 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="462,query">
+				<port id="2" precision="FP32" names="420,key">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="426" name="__module.encoder.mid_block.attentions.0/aten::size/ShapeOf_3" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
+		<layer id="381" name="Constant_95427" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="28710564" size="32" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="382" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape_2" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
-			</input>
-			<output>
 				<port id="1" precision="I64">
-					<dim>3</dim>
+					<dim>4</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="427" name="Constant_624244" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704784" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+			</input>
 			<output>
-				<port id="0" precision="I64">
+				<port id="2" precision="FP32" names="434">
+					<dim>-1</dim>
+					<dim>-1</dim>
 					<dim>1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="428" name="__module.encoder.mid_block.attentions.0/aten::size/Constant_3" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="383" name="Constant_95259" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="28710596" size="32" />
 			<output>
-				<port id="0" precision="I32" />
+				<port id="0" precision="I64">
+					<dim>4</dim>
+				</port>
 			</output>
 		</layer>
-		<layer id="429" name="__module.encoder.mid_block.attentions.0/aten::size/Gather_4" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="384" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_4" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>3</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>512</dim>
 				</port>
 				<port id="1" precision="I64">
-					<dim>1</dim>
+					<dim>4</dim>
 				</port>
-				<port id="2" precision="I32" />
 			</input>
 			<output>
-				<port id="3" precision="I64" names="454">
+				<port id="2" precision="FP32" names="435">
+					<dim>-1</dim>
 					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="430" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_0_1" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704820" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="385" name="self.encoder.mid_block.attentions.0.to_v.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512" offset="28976356" size="262144" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="431" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_1_1" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="57232200" size="8" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="386" name="Convert_123662" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="432" name="self.encoder.mid_block.attentions.0.to_k.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512" offset="57232208" size="524288" />
+		<layer id="387" name="self.encoder.mid_block.attentions.0.to_v.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1" offset="29238500" size="512" />
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.attentions.0.to_k.weight">
-					<dim>512</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="433" name="self.encoder.mid_block.attentions.0.to_k.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="388" name="Convert_123665" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>512</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>512</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="434" name="__module.encoder.mid_block.attentions.0.to_k/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="true" transpose_b="true" />
+		<layer id="389" name="self.encoder.mid_block.attentions.0.to_v.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="435" name="Constant_624639_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 512" offset="57756496" size="1024" />
+		<layer id="390" name="self.encoder.mid_block.attentions.0.to_v.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1" offset="29239012" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
+					<dim>512</dim>
 					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="391" name="self.encoder.mid_block.attentions.0.to_v.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
 					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="436" name="Constant_624639" type="Convert" version="opset1">
+		<layer id="392" name="self.encoder.mid_block.attentions.0.to_v.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</input>
 			<output>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="437" name="__module.encoder.mid_block.attentions.0.to_k/aten::linear/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="393" name="__module.encoder.mid_block.attentions.0.to_v/aten::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="true" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
+					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="465,key">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="438" name="__module.encoder.mid_block.attentions.0/aten::size/ShapeOf_4" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
-			<input>
+		<layer id="394" name="Constant_95312" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29240036" size="2048" />
+			<output>
 				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 					<dim>512</dim>
 				</port>
-			</input>
-			<output>
-				<port id="1" precision="I64">
-					<dim>3</dim>
-				</port>
 			</output>
 		</layer>
-		<layer id="439" name="__module.encoder.mid_block.attentions.0/aten::size/Constant_4" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="440" name="__module.encoder.mid_block.attentions.0/aten::size/Gather_5" type="Gather" version="opset8">
-			<data batch_dims="0" />
+		<layer id="395" name="__module.encoder.mid_block.attentions.0.to_v/aten::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>3</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
-			<output>
-				<port id="3" precision="I64" names="469" />
-			</output>
-		</layer>
-		<layer id="441" name="__module.encoder.mid_block.attentions.0/aten::floor_divide/Floor" type="Floor" version="opset1">
-			<input>
-				<port id="0" precision="I64" />
-			</input>
-			<output>
-				<port id="1" precision="I64" names="471,472,473,474,486,487,head_dim" />
-			</output>
-		</layer>
-		<layer id="442" name="Constant_764436" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704820" size="8" />
-			<output>
-				<port id="0" precision="I64">
+				<port id="1" precision="FP32">
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="443" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_2" type="Reshape" version="opset1">
-			<data special_zero="false" />
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64">
 					<dim>1</dim>
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
+				<port id="2" precision="FP32" names="423,value">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="444" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Concat_1" type="Concat" version="opset1">
-			<data axis="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="3" precision="I64">
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="396" name="Constant_95428" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="28710564" size="32" />
 			<output>
-				<port id="4" precision="I64" names="475,478,481">
+				<port id="0" precision="I64">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="445" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="397" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape_3" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -8005,7 +6873,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="476">
+				<port id="2" precision="FP32" names="437">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1</dim>
@@ -8013,18 +6881,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="446" name="Constant_624467" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="57757520" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="398" name="Constant_95263" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="28710596" size="32" />
 			<output>
 				<port id="0" precision="I64">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="447" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_3" type="Reshape" version="opset1">
+		<layer id="399" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_5" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8038,7 +6903,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="477">
+				<port id="2" precision="FP32" names="438">
 					<dim>-1</dim>
 					<dim>1</dim>
 					<dim>-1</dim>
@@ -8046,165 +6911,51 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="448" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape_2" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="400" name="__module.encoder.mid_block.attentions.0/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
+			<data causal="false" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
+					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>4</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="479">
-					<dim>-1</dim>
+				<port id="1" precision="FP32">
 					<dim>-1</dim>
 					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="449" name="Constant_624469" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="57757520" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="450" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_4" type="Reshape" version="opset1">
-			<data special_zero="true" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
 					<dim>-1</dim>
-					<dim>1</dim>
 					<dim>512</dim>
 				</port>
-				<port id="1" precision="I64">
-					<dim>4</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="480">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
 					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="451" name="self.encoder.mid_block.attentions.0.to_v.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512" offset="57757552" size="524288" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.attentions.0.to_v.weight">
-					<dim>512</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="452" name="self.encoder.mid_block.attentions.0.to_v.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>512</dim>
-					<dim>512</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>512</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="453" name="__module.encoder.mid_block.attentions.0.to_v/aten::linear/MatMul" type="MatMul" version="opset1">
-			<data transpose_a="true" transpose_b="true" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>512</dim>
-					<dim>512</dim>
-				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="3" precision="FP32" names="439,hidden_states.35">
 					<dim>-1</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="454" name="Constant_624640_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 512" offset="58281840" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>1</dim>
+					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="455" name="Constant_624640" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</input>
+		<layer id="401" name="Constant_95265" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="29242084" size="32" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
+				<port id="0" precision="I64">
+					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="456" name="__module.encoder.mid_block.attentions.0.to_v/aten::linear/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
+		<layer id="402" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_6" type="Reshape" version="opset1">
+			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>512</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="468,value">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="457" name="__module.encoder.mid_block.attentions.0/aten::view/Reshape_3" type="Reshape" version="opset1">
-			<data special_zero="false" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
@@ -8213,7 +6964,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="482">
+				<port id="2" precision="FP32" names="440">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>1</dim>
@@ -8221,18 +6972,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="458" name="Constant_624473" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="57757520" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="403" name="Constant_95429" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="29242116" size="24" />
 			<output>
 				<port id="0" precision="I64">
-					<dim>4</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="459" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_5" type="Reshape" version="opset1">
+		<layer id="404" name="__module.encoder.mid_block.attentions.0/aten::reshape/Reshape" type="Reshape" version="opset1">
 			<data special_zero="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8242,136 +6990,114 @@
 					<dim>512</dim>
 				</port>
 				<port id="1" precision="I64">
-					<dim>4</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="483">
+				<port id="2" precision="FP32" names="444,445,hidden_states.37">
 					<dim>-1</dim>
-					<dim>1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="460" name="__module.encoder.mid_block.attentions.0/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
-			<data causal="false" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>1</dim>
-					<dim>-1</dim>
+		<layer id="405" name="self.encoder.mid_block.attentions.0.to_out.0.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512" offset="29242140" size="262144" />
+			<output>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>1</dim>
-					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>1</dim>
-					<dim>-1</dim>
+			</output>
+		</layer>
+		<layer id="406" name="Convert_123695" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="3" precision="FP32" names="484,hidden_states.35">
-					<dim>-1</dim>
-					<dim>1</dim>
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="461" name="Constant_624475" type="Const" version="opset1">
-			<data element_type="i64" shape="4" offset="58282864" size="32" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="407" name="self.encoder.mid_block.attentions.0.to_out.0.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1" offset="29504284" size="512" />
 			<output>
-				<port id="0" precision="I64">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="462" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_6" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="408" name="Convert_123698" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>1</dim>
-					<dim>-1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>4</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="485">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="463" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Concat_4" type="Concat" version="opset1">
-			<data axis="0" />
+		<layer id="409" name="self.encoder.mid_block.attentions.0.to_out.0.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
-				<port id="2" precision="I64">
+				<port id="1" precision="FP16">
+					<dim>512</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="3" precision="I64" names="488">
-					<dim>3</dim>
+				<port id="2" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="464" name="__module.encoder.mid_block.attentions.0/aten::reshape/Reshape" type="Reshape" version="opset1">
-			<data special_zero="false" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>3</dim>
-				</port>
-			</input>
+		<layer id="410" name="self.encoder.mid_block.attentions.0.to_out.0.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1" offset="29504796" size="1024" />
 			<output>
-				<port id="2" precision="FP32" names="489,490,hidden_states.37">
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="465" name="self.encoder.mid_block.attentions.0.to_out.0.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512" offset="58282896" size="524288" />
+		<layer id="411" name="self.encoder.mid_block.attentions.0.to_out.0.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>512</dim>
+					<dim>512</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>512</dim>
+					<dim>1</dim>
+				</port>
+			</input>
 			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.attentions.0.to_out.0.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="466" name="self.encoder.mid_block.attentions.0.to_out.0.weight" type="Convert" version="opset1">
+		<layer id="412" name="self.encoder.mid_block.attentions.0.to_out.0.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -8385,7 +7111,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="467" name="__module.encoder.mid_block.attentions.0.to_out.0/aten::linear/MatMul" type="MatMul" version="opset1">
+		<layer id="413" name="__module.encoder.mid_block.attentions.0.to_out.0/aten::linear/MatMul" type="MatMul" version="opset1">
 			<data transpose_a="false" transpose_b="true" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8406,37 +7132,17 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="468" name="Constant_624641_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 512" offset="58807184" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="469" name="Constant_624641" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>512</dim>
-				</port>
-			</input>
+		<layer id="414" name="Constant_95313" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 512" offset="29505820" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="470" name="__module.encoder.mid_block.attentions.0.to_out.0/aten::linear/Add" type="Add" version="opset1">
+		<layer id="415" name="__module.encoder.mid_block.attentions.0.to_out.0/aten::linear/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8451,22 +7157,22 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="493,input.93">
+				<port id="2" precision="FP32" names="448,input.93">
 					<dim>-1</dim>
 					<dim>-1</dim>
 					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="471" name="__module.encoder.mid_block.attentions.0/aten::transpose/ScatterElementsUpdate_7" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="56704828" size="12" />
+		<layer id="416" name="__module.encoder.mid_block.attentions.0/aten::transpose/Constant_7" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="28440728" size="12" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="472" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_7" type="Transpose" version="opset1">
+		<layer id="417" name="__module.encoder.mid_block.attentions.0/aten::transpose/Transpose_7" type="Transpose" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -8478,80 +7184,30 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="495">
+				<port id="2" precision="FP32" names="450">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="473" name="Constant_764437" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704820" size="8" />
-			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="474" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_1_5" type="Reshape" version="opset1">
-			<data special_zero="false" />
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="475" name="Constant_764438" type="Const" version="opset1">
-			<data element_type="i64" shape="1" offset="56704820" size="8" />
-			<output>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="476" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Reshape_2_3" type="Reshape" version="opset1">
-			<data special_zero="false" />
+		<layer id="418" name="__module.encoder.mid_block.attentions.0/aten::size/ShapeOf" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
 			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="477" name="__module.encoder.mid_block.attentions.0/prim::ListConstruct/Concat_5" type="Concat" version="opset1">
-			<data axis="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
 				<port id="1" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="3" precision="I64">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="4" precision="I64" names="496">
 					<dim>4</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="478" name="__module.encoder.mid_block.attentions.0/aten::reshape/Reshape_1" type="Reshape" version="opset1">
+		<layer id="419" name="__module.encoder.mid_block.attentions.0/aten::reshape/Reshape_1" type="Reshape" version="opset1">
 			<data special_zero="false" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8564,7 +7220,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="497,hidden_states.41">
+				<port id="2" precision="FP32" names="452,hidden_states.41">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -8572,7 +7228,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="479" name="__module.encoder.mid_block.attentions.0/aten::add/Add" type="Add" version="opset1">
+		<layer id="420" name="__module.encoder.mid_block.attentions.0/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8589,7 +7245,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="498,499,hidden_states.43,input.95">
+				<port id="2" precision="FP32" names="453,454,hidden_states.43,input.95">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -8597,19 +7253,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="480" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="421" name="self.encoder.mid_block.resnets.1.norm1.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="29507868" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.1.norm1.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="481" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="422" name="self.encoder.mid_block.resnets.1.norm1.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="29509916" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.1.norm1.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="423" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -8617,221 +7278,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="462,input.97">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="482" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="483" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="424" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_18" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="484" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="463">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="425" name="self.encoder.mid_block.resnets.1.conv1.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="29511964" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="485" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="426" name="Convert_123574" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="486" name="Constant_624642_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="58808208" size="1024" />
+		<layer id="427" name="self.encoder.mid_block.resnets.1.conv1.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="31871260" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="487" name="Constant_624642" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="428" name="Convert_123577" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="488" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="429" name="self.encoder.mid_block.resnets.1.conv1.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="489" name="Constant_624643_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="58809232" size="1024" />
+		<layer id="430" name="self.encoder.mid_block.resnets.1.conv1.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="31871772" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="490" name="Constant_624643" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="431" name="self.encoder.mid_block.resnets.1.conv1.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="491" name="__module.encoder.mid_block.resnets.1.norm1/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="507,input.97">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="492" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_18" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="508">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="493" name="self.encoder.mid_block.resnets.1.conv1.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="58810256" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.resnets.1.conv1.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -8839,11 +7433,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="494" name="self.encoder.mid_block.resnets.1.conv1.weight" type="Convert" version="opset1">
+		<layer id="432" name="self.encoder.mid_block.resnets.1.conv1.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -8861,7 +7452,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="495" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="433" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8886,32 +7477,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="496" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="63528848" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="497" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="434" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="31872796" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -8919,7 +7488,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="498" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="435" name="__module.encoder.mid_block.resnets.1.conv1/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -8936,7 +7505,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="515,input.99">
+				<port id="2" precision="FP32" names="470,input.99">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -8944,19 +7513,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="499" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="436" name="self.encoder.mid_block.resnets.1.norm2.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="31874844" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.1.norm2.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="500" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="437" name="self.encoder.mid_block.resnets.1.norm2.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="31876892" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.mid_block.resnets.1.norm2.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="438" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -8964,221 +7538,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="473,input.101">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="501" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="502" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="439" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_19" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="503" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="474,input.103">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="440" name="self.encoder.mid_block.resnets.1.conv2.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 512, 3, 3" offset="31878940" size="2359296" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="504" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="441" name="Convert_123585" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>512</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="505" name="Constant_624644_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="63529872" size="1024" />
+		<layer id="442" name="self.encoder.mid_block.resnets.1.conv2.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="512, 1, 1, 1" offset="34238236" size="512" />
 			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="506" name="Constant_624644" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="443" name="Convert_123588" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
+				<port id="0" precision="U8">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="507" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="444" name="self.encoder.mid_block.resnets.1.conv2.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="508" name="Constant_624645_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="63530896" size="1024" />
+		<layer id="445" name="self.encoder.mid_block.resnets.1.conv2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="512, 1, 1, 1" offset="34238748" size="1024" />
 			<output>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="509" name="Constant_624645" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="446" name="self.encoder.mid_block.resnets.1.conv2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="510" name="__module.encoder.mid_block.resnets.1.norm2/aten::group_norm/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="518,input.101">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="511" name="__module.decoder.mid_block.resnets.1.nonlinearity/aten::silu/Swish_19" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="519,input.103">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="512" name="self.encoder.mid_block.resnets.1.conv2.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="512, 512, 3, 3" offset="63531920" size="4718592" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.mid_block.resnets.1.conv2.weight">
+				<port id="2" precision="FP16">
 					<dim>512</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -9186,11 +7693,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="513" name="self.encoder.mid_block.resnets.1.conv2.weight" type="Convert" version="opset1">
+		<layer id="447" name="self.encoder.mid_block.resnets.1.conv2.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>512</dim>
@@ -9208,7 +7712,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="514" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="448" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -9233,32 +7737,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="515" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="68250512" size="1024" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="516" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="449" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 512, 1, 1" offset="34239772" size="2048" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>512</dim>
 					<dim>1</dim>
@@ -9266,7 +7748,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="517" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="450" name="__module.encoder.mid_block.resnets.1.conv2/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -9283,7 +7765,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="527,hidden_states">
+				<port id="2" precision="FP32" names="482,hidden_states">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -9291,7 +7773,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="518" name="__module.encoder.mid_block.resnets.1/aten::add/Add" type="Add" version="opset1">
+		<layer id="451" name="__module.encoder.mid_block.resnets.1/aten::add/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -9308,7 +7790,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="528,529,input.105">
+				<port id="2" precision="FP32" names="483,484,input.105">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
@@ -9316,19 +7798,24 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="519" name="__module.encoder.conv_norm_out/aten::group_norm/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="3" offset="7168" size="12" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
+		<layer id="452" name="self.encoder.conv_norm_out.weight" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="34241820" size="2048" />
 			<output>
-				<port id="0" precision="I32">
-					<dim>3</dim>
+				<port id="0" precision="FP32" names="self.encoder.conv_norm_out.weight">
+					<dim>512</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="520" name="__module.encoder.conv_norm_out/aten::group_norm/Reshape" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="453" name="self.encoder.conv_norm_out.bias" type="Const" version="opset1">
+			<data element_type="f32" shape="512" offset="34243868" size="2048" />
+			<output>
+				<port id="0" precision="FP32" names="self.encoder.conv_norm_out.bias">
+					<dim>512</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="454" name="__module.encoder.conv_norm_out/aten::group_norm/GroupNormalization" type="GroupNormalization" version="opset12">
+			<data num_groups="32" epsilon="9.9999999747524271e-07" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -9336,221 +7823,154 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I32">
-					<dim>3</dim>
+				<port id="1" precision="FP32">
+					<dim>512</dim>
+				</port>
+				<port id="2" precision="FP32">
+					<dim>512</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
+				<port id="3" precision="FP32" names="487,input">
+					<dim>-1</dim>
+					<dim>512</dim>
 					<dim>-1</dim>
-					<dim>32</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="521" name="__module.encoder.conv_norm_out/aten::group_norm/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="522" name="__module.encoder.conv_norm_out/aten::group_norm/MVN" type="MVN" version="opset6">
-			<data eps="9.9999999747524271e-07" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+		<layer id="455" name="__module.encoder.conv_act/aten::silu/Swish" type="Swish" version="opset4">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>32</dim>
+					<dim>512</dim>
+					<dim>-1</dim>
 					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="523" name="__module.encoder.conv_norm_out/aten::group_norm/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
+				<port id="1" precision="FP32" names="488">
 					<dim>-1</dim>
 					<dim>512</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-			</input>
+			</output>
+		</layer>
+		<layer id="456" name="self.encoder.conv_out.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="8, 512, 3, 3" offset="34245916" size="36864" />
 			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>8</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="524" name="__module.encoder.conv_norm_out/aten::group_norm/Reshape_1" type="Reshape" version="opset1">
-			<data special_zero="true" />
+		<layer id="457" name="Convert_123772" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>32</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>4</dim>
+				<port id="0" precision="U8">
+					<dim>8</dim>
+					<dim>512</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
+					<dim>8</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="525" name="Constant_624646_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="68251536" size="1024" />
+		<layer id="458" name="self.encoder.conv_out.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="8, 1, 1, 1" offset="34282780" size="8" />
 			<output>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
+					<dim>8</dim>
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="526" name="Constant_624646" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="459" name="Convert_123775" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
+					<dim>8</dim>
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
+					<dim>8</dim>
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="527" name="__module.encoder.conv_norm_out/aten::group_norm/Multiply" type="Multiply" version="opset1">
+		<layer id="460" name="self.encoder.conv_out.weight/zero_point/subtract" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>8</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
+					<dim>8</dim>
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
+					<dim>8</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="528" name="Constant_624647_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 512, 1, 1" offset="68252560" size="1024" />
+		<layer id="461" name="self.encoder.conv_out.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="8, 1, 1, 1" offset="34282788" size="16" />
 			<output>
 				<port id="0" precision="FP16">
+					<dim>8</dim>
 					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="529" name="Constant_624647" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>512</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="530" name="__module.encoder.conv_norm_out/aten::group_norm/Add" type="Add" version="opset1">
+		<layer id="462" name="self.encoder.conv_out.weight/fq_weights_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="0" precision="FP16">
+					<dim>8</dim>
 					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
 				</port>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
+					<dim>8</dim>
 					<dim>1</dim>
-					<dim>512</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="532,input">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="531" name="__module.encoder.conv_act/aten::silu/Swish" type="Swish" version="opset4">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32" names="533">
-					<dim>-1</dim>
-					<dim>512</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="532" name="self.encoder.conv_out.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="8, 512, 3, 3" offset="68253584" size="73728" />
-			<output>
-				<port id="0" precision="FP16" names="self.encoder.conv_out.weight">
+				<port id="2" precision="FP16">
 					<dim>8</dim>
 					<dim>512</dim>
 					<dim>3</dim>
@@ -9558,11 +7978,8 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="533" name="self.encoder.conv_out.weight" type="Convert" version="opset1">
+		<layer id="463" name="self.encoder.conv_out.weight/fq_weights_1/convert" type="Convert" version="opset1">
 			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
 			<input>
 				<port id="0" precision="FP16">
 					<dim>8</dim>
@@ -9580,7 +7997,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="534" name="__module.encoder.conv_out/aten::_convolution/Convolution" type="Convolution" version="opset1">
+		<layer id="464" name="__module.encoder.conv_out/aten::_convolution/Convolution" type="Convolution" version="opset1">
 			<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
@@ -9605,32 +8022,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="535" name="__module.encoder.conv_out/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 8, 1, 1" offset="68327312" size="16" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>8</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="536" name="__module.encoder.conv_out/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>8</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="465" name="__module.encoder.conv_out/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 8, 1, 1" offset="34282804" size="32" />
 			<output>
-				<port id="1" precision="FP32">
+				<port id="0" precision="FP32">
 					<dim>1</dim>
 					<dim>8</dim>
 					<dim>1</dim>
@@ -9638,7 +8033,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="537" name="__module.encoder.conv_out/aten::_convolution/Add" type="Add" version="opset1">
+		<layer id="466" name="__module.encoder.conv_out/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
@@ -9655,7 +8050,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="540">
+				<port id="2" precision="FP32" names="495">
 					<dim>-1</dim>
 					<dim>8</dim>
 					<dim>-1</dim>
@@ -9663,10 +8058,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="538" name="self.quant_conv.weight_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="8, 8, 1, 1" offset="68327328" size="128" />
+		<layer id="467" name="self.quant_conv.weight" type="Const" version="opset1">
+			<data element_type="u8" shape="8, 8, 1, 1" offset="34282836" size="64" />
 			<output>
-				<port id="0" precision="FP16" names="self.quant_conv.weight">
+				<port id="0" precision="U8">
 					<dim>8</dim>
 					<dim>8</dim>
 					<dim>1</dim>
@@ -9674,13 +8069,10 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="539" name="self.quant_conv.weight" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="468" name="Convert_123805" type="Convert" version="opset1">
+			<data destination_type="f16" />
 			<input>
-				<port id="0" precision="FP16">
+				<port id="0" precision="U8">
 					<dim>8</dim>
 					<dim>8</dim>
 					<dim>1</dim>
@@ -9688,7 +8080,7 @@
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32">
+				<port id="1" precision="FP16">
 					<dim>8</dim>
 					<dim>8</dim>
 					<dim>1</dim>
@@ -9696,253 +8088,118 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="540" name="__module.quant_conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
-			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+		<layer id="469" name="self.quant_conv.weight/zero_point" type="Const" version="opset1">
+			<data element_type="u8" shape="8, 1, 1, 1" offset="34282900" size="8" />
+			<output>
+				<port id="0" precision="U8">
 					<dim>8</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
-				<port id="1" precision="FP32">
-					<dim>8</dim>
+			</output>
+		</layer>
+		<layer id="470" name="Convert_123808" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="U8">
 					<dim>8</dim>
 					<dim>1</dim>
 					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>8</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="541" name="__module.quant_conv/aten::_convolution/Reshape_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 8, 1, 1" offset="68327456" size="16" />
-			<output>
-				<port id="0" precision="FP16">
 					<dim>1</dim>
-					<dim>8</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="542" name="__module.quant_conv/aten::_convolution/Reshape" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
+		<layer id="471" name="self.quant_conv.weight/zero_point/subtract" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP16">
-					<dim>1</dim>
 					<dim>8</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
 					<dim>8</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="543" name="__module.quant_conv/aten::_convolution/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
+				<port id="1" precision="FP16">
 					<dim>8</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
 					<dim>1</dim>
-					<dim>8</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="FP32" names="551">
-					<dim>-1</dim>
+				<port id="2" precision="FP16">
 					<dim>8</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="544" name="12" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="57232200" size="8" />
-			<output>
-				<port id="0" precision="I64" names="12" />
-			</output>
-		</layer>
-		<layer id="545" name="prim::ListUnpack/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
 					<dim>8</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="546" name="Constant_618006" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="56704792" size="4" />
-			<output>
-				<port id="0" precision="I32">
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="547" name="prim::ListUnpack/Gather" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32">
 					<dim>1</dim>
 				</port>
-			</input>
-			<output>
-				<port id="3" precision="I32" />
-			</output>
-		</layer>
-		<layer id="548" name="prim::ListUnpack/Convert" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="7180" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="549" name="prim::ListUnpack/Divide" type="Divide" version="opset1">
-			<data auto_broadcast="numpy" m_pythondiv="true" />
-			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I32" />
-			</output>
-		</layer>
-		<layer id="550" name="prim::ListUnpack/Mod" type="Mod" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I32" />
 			</output>
 		</layer>
-		<layer id="551" name="prim::ListUnpack/Greater" type="Greater" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32">
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="472" name="self.quant_conv.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="8, 1, 1, 1" offset="34282908" size="16" />
 			<output>
-				<port id="2" precision="BOOL">
+				<port id="0" precision="FP16">
+					<dim>8</dim>
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="552" name="prim::ListUnpack/Convert_0" type="Convert" version="opset1">
-			<data destination_type="i32" />
-			<input>
-				<port id="0" precision="BOOL">
 					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="553" name="prim::ListUnpack/Add" type="Add" version="opset1">
+		<layer id="473" name="self.quant_conv.weight/fq_weights_1" type="Multiply" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
-				<port id="0" precision="I32" />
-				<port id="1" precision="I32">
+				<port id="0" precision="FP16">
+					<dim>8</dim>
+					<dim>8</dim>
 					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="I32">
 					<dim>1</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="554" name="Constant_618015" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="68327472" size="4" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<output>
-				<port id="0" precision="I32">
+				<port id="1" precision="FP16">
+					<dim>8</dim>
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="555" name="prim::ListUnpack/Broadcast" type="Broadcast" version="opset3">
-			<data mode="numpy" />
-			<input>
-				<port id="0" precision="I32">
 					<dim>1</dim>
-				</port>
-				<port id="1" precision="I32">
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I32">
+				<port id="2" precision="FP16">
+					<dim>8</dim>
+					<dim>8</dim>
 					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="556" name="Constant_618007" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="68327476" size="4" />
-			<output>
-				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="557" name="prim::ListUnpack/Concat" type="Concat" version="opset1">
-			<data axis="0" />
+		<layer id="474" name="self.quant_conv.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
 			<input>
-				<port id="0" precision="I32">
+				<port id="0" precision="FP16">
+					<dim>8</dim>
+					<dim>8</dim>
 					<dim>1</dim>
-				</port>
-				<port id="1" precision="I32">
 					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="2" precision="I32">
-					<dim>2</dim>
+				<port id="1" precision="FP32">
+					<dim>8</dim>
+					<dim>8</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="558" name="prim::ListUnpack/VariadicSplit" type="VariadicSplit" version="opset1">
+		<layer id="475" name="__module.quant_conv/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -9950,628 +8207,63 @@
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32">
-					<dim>2</dim>
-				</port>
-			</input>
-			<output>
-				<port id="3" precision="FP32" names="14">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="4" precision="FP32" names="15">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="559" name="aten::clamp/Minimum" type="Clamp" version="opset1">
-			<data min="-30" max="20" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
+				<port id="1" precision="FP32">
+					<dim>8</dim>
+					<dim>8</dim>
+					<dim>1</dim>
+					<dim>1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="18">
+				<port id="2" precision="FP32">
 					<dim>-1</dim>
-					<dim>4</dim>
+					<dim>8</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="560" name="Constant_624648_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1, 1" offset="68327480" size="2" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="561" name="Constant_624648" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
+		<layer id="476" name="__module.quant_conv/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 8, 1, 1" offset="34282924" size="32" />
 			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
+				<port id="0" precision="FP32">
 					<dim>1</dim>
+					<dim>8</dim>
 					<dim>1</dim>
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="562" name="aten::mul/Multiply" type="Multiply" version="opset1">
+		<layer id="477" name="__module.quant_conv/aten::_convolution/Add" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>4</dim>
+					<dim>8</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 				<port id="1" precision="FP32">
 					<dim>1</dim>
+					<dim>8</dim>
 					<dim>1</dim>
 					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="20">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="563" name="aten::exp/Exp" type="Exp" version="opset1">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="1" precision="FP32" names="21">
+				<port id="2" precision="FP32" names="latent_parameters">
 					<dim>-1</dim>
-					<dim>4</dim>
+					<dim>8</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="564" name="aten::size/ShapeOf" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
+		<layer id="478" name="Result_91502" type="Result" version="opset1">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I64">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="565" name="22" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="56704784" size="8" />
-			<output>
-				<port id="0" precision="I64" names="22" />
-			</output>
-		</layer>
-		<layer id="566" name="aten::size/Constant" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="567" name="aten::size/Gather" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
-			<output>
-				<port id="3" precision="I64" names="23,25" />
-			</output>
-		</layer>
-		<layer id="568" name="Constant_615241" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="569" name="Unsqueeze_615242" type="Unsqueeze" version="opset1">
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="570" name="26" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="57232200" size="8" />
-			<output>
-				<port id="0" precision="I64" names="26" />
-			</output>
-		</layer>
-		<layer id="571" name="aten::size/Constant_1" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="572" name="aten::size/Gather_1" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
-			<output>
-				<port id="3" precision="I64" names="27,29" />
-			</output>
-		</layer>
-		<layer id="573" name="Unsqueeze_615243" type="Unsqueeze" version="opset1">
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="574" name="30" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="56704804" size="8" />
-			<output>
-				<port id="0" precision="I64" names="30" />
-			</output>
-		</layer>
-		<layer id="575" name="aten::size/Constant_2" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="576" name="aten::size/Gather_2" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
-			<output>
-				<port id="3" precision="I64" names="31,33" />
-			</output>
-		</layer>
-		<layer id="577" name="Unsqueeze_615244" type="Unsqueeze" version="opset1">
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="578" name="34" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="56704812" size="8" />
-			<output>
-				<port id="0" precision="I64" names="34" />
-			</output>
-		</layer>
-		<layer id="579" name="aten::size/Constant_3" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="56704792" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="580" name="aten::size/Gather_3" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I32" />
-			</input>
-			<output>
-				<port id="3" precision="I64" names="35,37" />
-			</output>
-		</layer>
-		<layer id="581" name="Unsqueeze_615245" type="Unsqueeze" version="opset1">
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I32" />
-			</input>
-			<output>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="582" name="Concat_615246" type="Concat" version="opset1">
-			<data axis="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="1" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="2" precision="I64">
-					<dim>1</dim>
-				</port>
-				<port id="3" precision="I64">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="4" precision="I64">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="583" name="aten::randn/Convert" type="Convert" version="opset1">
-			<data destination_type="i32" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>4</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I32">
-					<dim>4</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="584" name="aten::randn/Constant_1" type="Const" version="opset1">
-			<data element_type="f32" shape="1" offset="68327482" size="4" />
-			<output>
-				<port id="0" precision="FP32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="585" name="aten::randn/Constant_2_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1" offset="68327486" size="2" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="586" name="aten::randn/Constant_2" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="587" name="aten::randn/RandomUniform" type="RandomUniform" version="opset8">
-			<data output_type="f32" op_seed="9001317" global_seed="0" />
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="I32">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-				</port>
-				<port id="2" precision="FP32">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="3" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="588" name="aten::randn/Log" type="Log" version="opset1">
-			<rt_info>
-				<attribute name="precise" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="589" name="Constant_624649_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1, 1, 1, 1" offset="68327488" size="2" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="590" name="Constant_624649" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="591" name="aten::randn/Multiply" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="592" name="aten::randn/Sqrt" type="Sqrt" version="opset1">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="593" name="Constant_624515" type="Const" version="opset1">
-			<data element_type="f32" shape="1" offset="68327490" size="4" />
-			<output>
-				<port id="0" precision="FP32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="594" name="Constant_624516_compressed" type="Const" version="opset1">
-			<data element_type="f16" shape="1" offset="68327494" size="2" />
-			<output>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="595" name="Constant_624516" type="Convert" version="opset1">
-			<data destination_type="f32" />
-			<rt_info>
-				<attribute name="decompression" version="0" />
-			</rt_info>
-			<input>
-				<port id="0" precision="FP16">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="596" name="aten::randn/Multiply_2" type="RandomUniform" version="opset8">
-			<data output_type="f32" op_seed="9011317" global_seed="0" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>4</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>1</dim>
-				</port>
-				<port id="2" precision="FP32">
-					<dim>1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="3" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="597" name="aten::randn/Cos" type="Cos" version="opset1">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="598" name="aten::randn/Multiply_3" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="44,52,sample">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="599" name="aten::mul/Multiply_1" type="Multiply" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="53">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="600" name="aten::add/Add" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="2" precision="FP32" names="latent_sample">
-					<dim>-1</dim>
-					<dim>4</dim>
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="601" name="Result_619345" type="Result" version="opset1">
-			<input>
-				<port id="0" precision="FP32">
-					<dim>-1</dim>
-					<dim>4</dim>
+					<dim>8</dim>
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
@@ -10579,684 +8271,531 @@
 		</layer>
 	</layers>
 	<edges>
-		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
+		<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="3" to-port="1" />
-		<edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
-		<edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
-		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
-		<edge from-layer="6" from-port="2" to-layer="45" to-port="0" />
-		<edge from-layer="6" from-port="2" to-layer="11" to-port="0" />
-		<edge from-layer="6" from-port="2" to-layer="8" to-port="0" />
-		<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
-		<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
-		<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
-		<edge from-layer="10" from-port="2" to-layer="12" to-port="0" />
-		<edge from-layer="11" from-port="1" to-layer="12" to-port="1" />
-		<edge from-layer="12" from-port="2" to-layer="15" 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="15" to-port="1" />
-		<edge from-layer="15" from-port="2" to-layer="18" 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="42" to-port="0" />
+		<edge from-layer="11" from-port="2" to-layer="14" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="14" to-port="1" />
+		<edge from-layer="13" from-port="0" to-layer="14" to-port="2" />
+		<edge from-layer="14" from-port="3" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="24" to-port="0" />
 		<edge from-layer="16" from-port="0" to-layer="17" to-port="0" />
-		<edge from-layer="17" from-port="1" to-layer="18" to-port="1" />
-		<edge from-layer="18" from-port="2" to-layer="19" to-port="0" />
-		<edge from-layer="19" from-port="1" to-layer="22" to-port="0" />
-		<edge from-layer="20" from-port="0" to-layer="21" to-port="0" />
-		<edge from-layer="21" from-port="1" to-layer="22" to-port="1" />
-		<edge from-layer="22" from-port="2" to-layer="25" to-port="0" />
-		<edge from-layer="23" from-port="0" to-layer="24" to-port="0" />
-		<edge from-layer="24" from-port="1" to-layer="25" to-port="1" />
-		<edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
-		<edge from-layer="25" from-port="2" to-layer="30" to-port="0" />
-		<edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
-		<edge from-layer="27" from-port="2" to-layer="29" to-port="0" />
-		<edge from-layer="28" from-port="0" to-layer="29" to-port="1" />
-		<edge from-layer="29" from-port="2" to-layer="31" to-port="0" />
-		<edge from-layer="30" from-port="1" to-layer="31" to-port="1" />
-		<edge from-layer="31" from-port="2" to-layer="34" to-port="0" />
-		<edge from-layer="32" from-port="0" to-layer="33" to-port="0" />
-		<edge from-layer="33" from-port="1" to-layer="34" to-port="1" />
-		<edge from-layer="34" from-port="2" to-layer="37" 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="37" to-port="1" />
+		<edge from-layer="17" from-port="1" to-layer="20" to-port="0" />
+		<edge from-layer="18" from-port="0" to-layer="19" to-port="0" />
+		<edge from-layer="19" from-port="1" to-layer="20" to-port="1" />
+		<edge from-layer="20" from-port="2" to-layer="22" to-port="0" />
+		<edge from-layer="21" from-port="0" to-layer="22" to-port="1" />
+		<edge from-layer="22" from-port="2" to-layer="23" to-port="0" />
+		<edge from-layer="23" from-port="1" to-layer="24" to-port="1" />
+		<edge from-layer="24" from-port="2" 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="29" to-port="0" />
+		<edge from-layer="27" from-port="0" to-layer="29" to-port="1" />
+		<edge from-layer="28" from-port="0" to-layer="29" to-port="2" />
+		<edge from-layer="29" from-port="3" to-layer="30" to-port="0" />
+		<edge from-layer="30" from-port="1" to-layer="39" to-port="0" />
+		<edge from-layer="31" from-port="0" to-layer="32" to-port="0" />
+		<edge from-layer="32" from-port="1" to-layer="35" to-port="0" />
+		<edge from-layer="33" from-port="0" to-layer="34" to-port="0" />
+		<edge from-layer="34" from-port="1" to-layer="35" to-port="1" />
+		<edge from-layer="35" from-port="2" to-layer="37" to-port="0" />
+		<edge from-layer="36" from-port="0" to-layer="37" to-port="1" />
 		<edge from-layer="37" from-port="2" to-layer="38" to-port="0" />
-		<edge from-layer="38" from-port="1" to-layer="41" to-port="0" />
-		<edge from-layer="39" from-port="0" to-layer="40" to-port="0" />
-		<edge from-layer="40" from-port="1" to-layer="41" to-port="1" />
-		<edge from-layer="41" from-port="2" to-layer="44" to-port="0" />
-		<edge from-layer="42" from-port="0" to-layer="43" to-port="0" />
-		<edge from-layer="43" from-port="1" to-layer="44" to-port="1" />
-		<edge from-layer="44" from-port="2" to-layer="45" to-port="1" />
-		<edge from-layer="45" from-port="2" to-layer="84" to-port="0" />
-		<edge from-layer="45" from-port="2" to-layer="50" to-port="0" />
-		<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
-		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
-		<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
-		<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
-		<edge from-layer="49" from-port="2" to-layer="51" to-port="0" />
+		<edge from-layer="38" from-port="1" to-layer="39" to-port="1" />
+		<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
+		<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
+		<edge from-layer="41" from-port="2" to-layer="42" to-port="1" />
+		<edge from-layer="42" from-port="2" to-layer="73" to-port="0" />
+		<edge from-layer="42" from-port="2" to-layer="45" to-port="0" />
+		<edge from-layer="43" from-port="0" to-layer="45" to-port="1" />
+		<edge from-layer="44" from-port="0" to-layer="45" to-port="2" />
+		<edge from-layer="45" from-port="3" to-layer="46" to-port="0" />
+		<edge from-layer="46" from-port="1" to-layer="55" to-port="0" />
+		<edge from-layer="47" from-port="0" to-layer="48" to-port="0" />
+		<edge from-layer="48" from-port="1" to-layer="51" 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="51" to-port="1" />
-		<edge from-layer="51" from-port="2" to-layer="54" to-port="0" />
-		<edge from-layer="52" from-port="0" to-layer="53" to-port="0" />
-		<edge from-layer="53" from-port="1" to-layer="54" to-port="1" />
-		<edge from-layer="54" from-port="2" to-layer="57" to-port="0" />
-		<edge from-layer="55" from-port="0" to-layer="56" to-port="0" />
-		<edge from-layer="56" from-port="1" to-layer="57" to-port="1" />
-		<edge from-layer="57" from-port="2" to-layer="58" to-port="0" />
-		<edge from-layer="58" from-port="1" to-layer="61" to-port="0" />
-		<edge from-layer="59" from-port="0" to-layer="60" to-port="0" />
-		<edge from-layer="60" from-port="1" to-layer="61" to-port="1" />
-		<edge from-layer="61" from-port="2" to-layer="64" to-port="0" />
+		<edge from-layer="51" from-port="2" to-layer="53" to-port="0" />
+		<edge from-layer="52" from-port="0" to-layer="53" to-port="1" />
+		<edge from-layer="53" from-port="2" to-layer="54" to-port="0" />
+		<edge from-layer="54" from-port="1" to-layer="55" to-port="1" />
+		<edge from-layer="55" from-port="2" to-layer="57" to-port="0" />
+		<edge from-layer="56" from-port="0" to-layer="57" to-port="1" />
+		<edge from-layer="57" from-port="2" to-layer="60" to-port="0" />
+		<edge from-layer="58" from-port="0" to-layer="60" to-port="1" />
+		<edge from-layer="59" from-port="0" to-layer="60" to-port="2" />
+		<edge from-layer="60" from-port="3" to-layer="61" to-port="0" />
+		<edge from-layer="61" from-port="1" to-layer="70" to-port="0" />
 		<edge from-layer="62" from-port="0" to-layer="63" to-port="0" />
-		<edge from-layer="63" from-port="1" to-layer="64" to-port="1" />
-		<edge from-layer="64" from-port="2" to-layer="66" to-port="0" />
-		<edge from-layer="64" from-port="2" to-layer="69" to-port="0" />
-		<edge from-layer="65" from-port="0" to-layer="66" to-port="1" />
+		<edge from-layer="63" from-port="1" to-layer="66" to-port="0" />
+		<edge from-layer="64" from-port="0" to-layer="65" to-port="0" />
+		<edge from-layer="65" from-port="1" to-layer="66" to-port="1" />
 		<edge from-layer="66" from-port="2" to-layer="68" to-port="0" />
 		<edge from-layer="67" from-port="0" to-layer="68" to-port="1" />
-		<edge from-layer="68" from-port="2" to-layer="70" to-port="0" />
+		<edge from-layer="68" from-port="2" to-layer="69" to-port="0" />
 		<edge from-layer="69" from-port="1" to-layer="70" to-port="1" />
-		<edge from-layer="70" from-port="2" to-layer="73" to-port="0" />
-		<edge from-layer="71" from-port="0" to-layer="72" to-port="0" />
-		<edge from-layer="72" from-port="1" to-layer="73" to-port="1" />
-		<edge from-layer="73" from-port="2" to-layer="76" to-port="0" />
+		<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="73" to-port="1" />
+		<edge from-layer="73" from-port="2" to-layer="82" to-port="0" />
 		<edge from-layer="74" from-port="0" to-layer="75" to-port="0" />
-		<edge from-layer="75" from-port="1" to-layer="76" to-port="1" />
-		<edge from-layer="76" from-port="2" to-layer="77" to-port="0" />
-		<edge from-layer="77" from-port="1" to-layer="80" to-port="0" />
-		<edge from-layer="78" from-port="0" to-layer="79" to-port="0" />
-		<edge from-layer="79" from-port="1" to-layer="80" to-port="1" />
-		<edge from-layer="80" from-port="2" to-layer="83" to-port="0" />
-		<edge from-layer="81" from-port="0" to-layer="82" to-port="0" />
-		<edge from-layer="82" from-port="1" to-layer="83" to-port="1" />
-		<edge from-layer="83" from-port="2" to-layer="84" to-port="1" />
-		<edge from-layer="84" from-port="2" to-layer="87" to-port="0" />
+		<edge from-layer="75" from-port="1" to-layer="78" to-port="0" />
+		<edge from-layer="76" from-port="0" to-layer="77" to-port="0" />
+		<edge from-layer="77" from-port="1" to-layer="78" to-port="1" />
+		<edge from-layer="78" from-port="2" to-layer="80" to-port="0" />
+		<edge from-layer="79" from-port="0" to-layer="80" to-port="1" />
+		<edge from-layer="80" from-port="2" to-layer="81" to-port="0" />
+		<edge from-layer="81" from-port="1" to-layer="82" to-port="1" />
+		<edge from-layer="82" from-port="2" to-layer="84" to-port="0" />
+		<edge from-layer="83" from-port="0" to-layer="84" to-port="1" />
+		<edge from-layer="84" from-port="2" to-layer="98" to-port="0" />
+		<edge from-layer="84" from-port="2" to-layer="93" to-port="0" />
 		<edge from-layer="85" from-port="0" 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="90" to-port="0" />
-		<edge from-layer="88" from-port="0" to-layer="89" to-port="0" />
-		<edge from-layer="89" from-port="1" to-layer="90" to-port="1" />
-		<edge from-layer="90" from-port="2" to-layer="101" to-port="0" />
-		<edge from-layer="90" from-port="2" to-layer="98" to-port="0" />
-		<edge from-layer="90" from-port="2" to-layer="93" to-port="0" />
-		<edge from-layer="91" from-port="0" to-layer="92" to-port="0" />
+		<edge from-layer="86" from-port="1" to-layer="89" to-port="0" />
+		<edge from-layer="87" from-port="0" to-layer="88" to-port="0" />
+		<edge from-layer="88" from-port="1" to-layer="89" to-port="1" />
+		<edge from-layer="89" from-port="2" to-layer="91" to-port="0" />
+		<edge from-layer="90" from-port="0" to-layer="91" to-port="1" />
+		<edge from-layer="91" from-port="2" to-layer="92" to-port="0" />
 		<edge from-layer="92" from-port="1" to-layer="93" to-port="1" />
-		<edge from-layer="93" from-port="2" to-layer="96" to-port="0" />
-		<edge from-layer="94" from-port="0" to-layer="95" to-port="0" />
-		<edge from-layer="95" from-port="1" to-layer="96" to-port="1" />
-		<edge from-layer="96" from-port="2" to-layer="135" to-port="0" />
-		<edge from-layer="97" from-port="0" to-layer="98" to-port="1" />
-		<edge from-layer="98" from-port="2" to-layer="100" to-port="0" />
-		<edge from-layer="99" from-port="0" to-layer="100" to-port="1" />
-		<edge from-layer="100" from-port="2" to-layer="102" to-port="0" />
-		<edge from-layer="101" from-port="1" to-layer="102" to-port="1" />
-		<edge from-layer="102" from-port="2" to-layer="105" to-port="0" />
-		<edge from-layer="103" from-port="0" to-layer="104" to-port="0" />
-		<edge from-layer="104" from-port="1" to-layer="105" to-port="1" />
-		<edge from-layer="105" from-port="2" to-layer="108" to-port="0" />
-		<edge from-layer="106" from-port="0" to-layer="107" to-port="0" />
+		<edge from-layer="93" from-port="2" to-layer="95" to-port="0" />
+		<edge from-layer="94" from-port="0" to-layer="95" to-port="1" />
+		<edge from-layer="95" from-port="2" to-layer="126" to-port="0" />
+		<edge from-layer="96" from-port="0" to-layer="98" to-port="1" />
+		<edge from-layer="97" from-port="0" to-layer="98" to-port="2" />
+		<edge from-layer="98" from-port="3" to-layer="99" to-port="0" />
+		<edge from-layer="99" from-port="1" to-layer="108" to-port="0" />
+		<edge from-layer="100" from-port="0" to-layer="101" to-port="0" />
+		<edge from-layer="101" from-port="1" to-layer="104" to-port="0" />
+		<edge from-layer="102" from-port="0" 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="108" to-port="1" />
-		<edge from-layer="108" from-port="2" to-layer="109" to-port="0" />
-		<edge from-layer="109" from-port="1" to-layer="112" to-port="0" />
-		<edge from-layer="110" from-port="0" to-layer="111" to-port="0" />
-		<edge from-layer="111" from-port="1" to-layer="112" to-port="1" />
-		<edge from-layer="112" from-port="2" to-layer="115" to-port="0" />
-		<edge from-layer="113" from-port="0" 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="115" from-port="2" to-layer="120" to-port="0" />
-		<edge from-layer="116" from-port="0" to-layer="117" to-port="1" />
-		<edge from-layer="117" from-port="2" to-layer="119" to-port="0" />
-		<edge from-layer="118" from-port="0" to-layer="119" to-port="1" />
+		<edge from-layer="108" from-port="2" to-layer="110" to-port="0" />
+		<edge from-layer="109" from-port="0" to-layer="110" to-port="1" />
+		<edge from-layer="110" from-port="2" to-layer="113" to-port="0" />
+		<edge from-layer="111" from-port="0" to-layer="113" to-port="1" />
+		<edge from-layer="112" from-port="0" to-layer="113" to-port="2" />
+		<edge from-layer="113" from-port="3" to-layer="114" to-port="0" />
+		<edge from-layer="114" from-port="1" to-layer="123" to-port="0" />
+		<edge from-layer="115" from-port="0" to-layer="116" to-port="0" />
+		<edge from-layer="116" from-port="1" to-layer="119" to-port="0" />
+		<edge from-layer="117" from-port="0" to-layer="118" to-port="0" />
+		<edge from-layer="118" from-port="1" to-layer="119" to-port="1" />
 		<edge from-layer="119" from-port="2" to-layer="121" to-port="0" />
-		<edge from-layer="120" from-port="1" to-layer="121" to-port="1" />
-		<edge from-layer="121" from-port="2" to-layer="124" to-port="0" />
-		<edge from-layer="122" from-port="0" to-layer="123" to-port="0" />
-		<edge from-layer="123" from-port="1" to-layer="124" to-port="1" />
-		<edge from-layer="124" from-port="2" to-layer="127" 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="127" to-port="1" />
-		<edge from-layer="127" from-port="2" to-layer="128" to-port="0" />
-		<edge from-layer="128" from-port="1" to-layer="131" to-port="0" />
-		<edge from-layer="129" from-port="0" to-layer="130" to-port="0" />
-		<edge from-layer="130" from-port="1" to-layer="131" to-port="1" />
-		<edge from-layer="131" from-port="2" to-layer="134" to-port="0" />
-		<edge from-layer="132" from-port="0" to-layer="133" to-port="0" />
-		<edge from-layer="133" from-port="1" to-layer="134" to-port="1" />
-		<edge from-layer="134" from-port="2" to-layer="135" to-port="1" />
-		<edge from-layer="135" from-port="2" to-layer="174" to-port="0" />
-		<edge from-layer="135" from-port="2" to-layer="140" to-port="0" />
+		<edge from-layer="120" from-port="0" to-layer="121" to-port="1" />
+		<edge from-layer="121" from-port="2" to-layer="122" to-port="0" />
+		<edge from-layer="122" from-port="1" to-layer="123" to-port="1" />
+		<edge from-layer="123" from-port="2" to-layer="125" to-port="0" />
+		<edge from-layer="124" from-port="0" to-layer="125" to-port="1" />
+		<edge from-layer="125" from-port="2" to-layer="126" to-port="1" />
+		<edge from-layer="126" from-port="2" to-layer="157" to-port="0" />
+		<edge from-layer="126" from-port="2" to-layer="129" to-port="0" />
+		<edge from-layer="127" from-port="0" to-layer="129" to-port="1" />
+		<edge from-layer="128" from-port="0" to-layer="129" to-port="2" />
+		<edge from-layer="129" from-port="3" to-layer="130" to-port="0" />
+		<edge from-layer="130" from-port="1" to-layer="139" to-port="0" />
+		<edge from-layer="131" from-port="0" to-layer="132" to-port="0" />
+		<edge from-layer="132" from-port="1" to-layer="135" to-port="0" />
+		<edge from-layer="133" from-port="0" to-layer="134" to-port="0" />
+		<edge from-layer="134" from-port="1" to-layer="135" to-port="1" />
 		<edge from-layer="135" from-port="2" to-layer="137" to-port="0" />
 		<edge from-layer="136" from-port="0" to-layer="137" to-port="1" />
-		<edge from-layer="137" from-port="2" to-layer="139" to-port="0" />
-		<edge from-layer="138" from-port="0" to-layer="139" to-port="1" />
+		<edge from-layer="137" from-port="2" to-layer="138" to-port="0" />
+		<edge from-layer="138" from-port="1" to-layer="139" to-port="1" />
 		<edge from-layer="139" from-port="2" to-layer="141" to-port="0" />
-		<edge from-layer="140" from-port="1" to-layer="141" to-port="1" />
+		<edge from-layer="140" from-port="0" to-layer="141" to-port="1" />
 		<edge from-layer="141" from-port="2" to-layer="144" to-port="0" />
-		<edge from-layer="142" from-port="0" to-layer="143" to-port="0" />
-		<edge from-layer="143" from-port="1" to-layer="144" to-port="1" />
-		<edge from-layer="144" from-port="2" to-layer="147" to-port="0" />
-		<edge from-layer="145" from-port="0" to-layer="146" to-port="0" />
-		<edge from-layer="146" from-port="1" to-layer="147" to-port="1" />
-		<edge from-layer="147" from-port="2" to-layer="148" to-port="0" />
-		<edge from-layer="148" from-port="1" to-layer="151" to-port="0" />
-		<edge from-layer="149" from-port="0" to-layer="150" to-port="0" />
-		<edge from-layer="150" from-port="1" to-layer="151" to-port="1" />
-		<edge from-layer="151" from-port="2" to-layer="154" to-port="0" />
-		<edge from-layer="152" from-port="0" to-layer="153" to-port="0" />
+		<edge from-layer="142" from-port="0" to-layer="144" to-port="1" />
+		<edge from-layer="143" from-port="0" to-layer="144" to-port="2" />
+		<edge from-layer="144" from-port="3" to-layer="145" to-port="0" />
+		<edge from-layer="145" from-port="1" to-layer="154" to-port="0" />
+		<edge from-layer="146" from-port="0" to-layer="147" to-port="0" />
+		<edge from-layer="147" from-port="1" to-layer="150" to-port="0" />
+		<edge from-layer="148" from-port="0" to-layer="149" to-port="0" />
+		<edge from-layer="149" from-port="1" to-layer="150" to-port="1" />
+		<edge from-layer="150" from-port="2" to-layer="152" to-port="0" />
+		<edge from-layer="151" from-port="0" to-layer="152" to-port="1" />
+		<edge from-layer="152" from-port="2" to-layer="153" to-port="0" />
 		<edge from-layer="153" from-port="1" to-layer="154" to-port="1" />
 		<edge from-layer="154" from-port="2" to-layer="156" to-port="0" />
-		<edge from-layer="154" from-port="2" to-layer="159" to-port="0" />
 		<edge from-layer="155" from-port="0" to-layer="156" to-port="1" />
-		<edge from-layer="156" from-port="2" to-layer="158" to-port="0" />
-		<edge from-layer="157" from-port="0" to-layer="158" to-port="1" />
-		<edge from-layer="158" from-port="2" to-layer="160" to-port="0" />
-		<edge from-layer="159" from-port="1" to-layer="160" to-port="1" />
-		<edge from-layer="160" from-port="2" to-layer="163" to-port="0" />
-		<edge from-layer="161" from-port="0" to-layer="162" to-port="0" />
-		<edge from-layer="162" from-port="1" to-layer="163" to-port="1" />
-		<edge from-layer="163" from-port="2" to-layer="166" to-port="0" />
-		<edge from-layer="164" from-port="0" to-layer="165" to-port="0" />
+		<edge from-layer="156" from-port="2" to-layer="157" to-port="1" />
+		<edge from-layer="157" from-port="2" to-layer="166" to-port="0" />
+		<edge from-layer="158" from-port="0" to-layer="159" to-port="0" />
+		<edge from-layer="159" from-port="1" to-layer="162" to-port="0" />
+		<edge from-layer="160" from-port="0" to-layer="161" to-port="0" />
+		<edge from-layer="161" from-port="1" 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="0" />
 		<edge from-layer="165" from-port="1" to-layer="166" to-port="1" />
-		<edge from-layer="166" from-port="2" to-layer="167" to-port="0" />
-		<edge from-layer="167" from-port="1" to-layer="170" to-port="0" />
-		<edge from-layer="168" from-port="0" to-layer="169" to-port="0" />
-		<edge from-layer="169" from-port="1" to-layer="170" to-port="1" />
-		<edge from-layer="170" from-port="2" to-layer="173" to-port="0" />
+		<edge from-layer="166" from-port="2" to-layer="168" to-port="0" />
+		<edge from-layer="167" from-port="0" to-layer="168" to-port="1" />
+		<edge from-layer="168" from-port="2" to-layer="182" to-port="0" />
+		<edge from-layer="168" from-port="2" to-layer="177" to-port="0" />
+		<edge from-layer="169" from-port="0" to-layer="170" to-port="0" />
+		<edge from-layer="170" from-port="1" to-layer="173" to-port="0" />
 		<edge from-layer="171" from-port="0" to-layer="172" to-port="0" />
 		<edge from-layer="172" from-port="1" to-layer="173" to-port="1" />
-		<edge from-layer="173" from-port="2" to-layer="174" to-port="1" />
-		<edge from-layer="174" from-port="2" to-layer="177" to-port="0" />
-		<edge from-layer="175" from-port="0" to-layer="176" to-port="0" />
+		<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="180" to-port="0" />
-		<edge from-layer="178" from-port="0" to-layer="179" to-port="0" />
-		<edge from-layer="179" from-port="1" to-layer="180" to-port="1" />
-		<edge from-layer="180" from-port="2" to-layer="183" to-port="0" />
-		<edge from-layer="180" from-port="2" to-layer="191" to-port="0" />
-		<edge from-layer="180" from-port="2" to-layer="188" to-port="0" />
-		<edge from-layer="181" from-port="0" to-layer="182" to-port="0" />
-		<edge from-layer="182" from-port="1" to-layer="183" to-port="1" />
-		<edge from-layer="183" from-port="2" to-layer="186" to-port="0" />
+		<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="210" to-port="0" />
+		<edge from-layer="180" from-port="0" to-layer="182" to-port="1" />
+		<edge from-layer="181" from-port="0" to-layer="182" to-port="2" />
+		<edge from-layer="182" from-port="3" to-layer="183" to-port="0" />
+		<edge from-layer="183" from-port="1" to-layer="192" to-port="0" />
 		<edge from-layer="184" from-port="0" to-layer="185" to-port="0" />
-		<edge from-layer="185" from-port="1" to-layer="186" to-port="1" />
-		<edge from-layer="186" from-port="2" to-layer="225" to-port="0" />
-		<edge from-layer="187" from-port="0" to-layer="188" to-port="1" />
+		<edge from-layer="185" from-port="1" to-layer="188" to-port="0" />
+		<edge from-layer="186" from-port="0" to-layer="187" to-port="0" />
+		<edge from-layer="187" from-port="1" to-layer="188" to-port="1" />
 		<edge from-layer="188" from-port="2" to-layer="190" to-port="0" />
 		<edge from-layer="189" from-port="0" to-layer="190" to-port="1" />
-		<edge from-layer="190" from-port="2" to-layer="192" to-port="0" />
+		<edge from-layer="190" from-port="2" to-layer="191" to-port="0" />
 		<edge from-layer="191" from-port="1" to-layer="192" to-port="1" />
-		<edge from-layer="192" from-port="2" to-layer="195" to-port="0" />
-		<edge from-layer="193" from-port="0" to-layer="194" to-port="0" />
-		<edge from-layer="194" from-port="1" to-layer="195" to-port="1" />
-		<edge from-layer="195" from-port="2" to-layer="198" to-port="0" />
-		<edge from-layer="196" from-port="0" to-layer="197" to-port="0" />
-		<edge from-layer="197" from-port="1" to-layer="198" to-port="1" />
-		<edge from-layer="198" from-port="2" to-layer="199" to-port="0" />
-		<edge from-layer="199" from-port="1" to-layer="202" to-port="0" />
-		<edge from-layer="200" from-port="0" to-layer="201" to-port="0" />
-		<edge from-layer="201" from-port="1" to-layer="202" to-port="1" />
-		<edge from-layer="202" from-port="2" to-layer="205" to-port="0" />
-		<edge from-layer="203" from-port="0" 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="205" from-port="2" to-layer="210" to-port="0" />
-		<edge from-layer="206" from-port="0" to-layer="207" to-port="1" />
+		<edge from-layer="192" from-port="2" to-layer="194" to-port="0" />
+		<edge from-layer="193" from-port="0" to-layer="194" to-port="1" />
+		<edge from-layer="194" from-port="2" to-layer="197" to-port="0" />
+		<edge from-layer="195" from-port="0" to-layer="197" to-port="1" />
+		<edge from-layer="196" from-port="0" to-layer="197" to-port="2" />
+		<edge from-layer="197" from-port="3" to-layer="198" to-port="0" />
+		<edge from-layer="198" from-port="1" to-layer="207" to-port="0" />
+		<edge from-layer="199" from-port="0" to-layer="200" to-port="0" />
+		<edge from-layer="200" from-port="1" to-layer="203" to-port="0" />
+		<edge from-layer="201" from-port="0" to-layer="202" to-port="0" />
+		<edge from-layer="202" from-port="1" to-layer="203" to-port="1" />
+		<edge from-layer="203" from-port="2" to-layer="205" to-port="0" />
+		<edge from-layer="204" from-port="0" to-layer="205" to-port="1" />
+		<edge from-layer="205" from-port="2" to-layer="206" to-port="0" />
+		<edge from-layer="206" from-port="1" to-layer="207" to-port="1" />
 		<edge from-layer="207" from-port="2" to-layer="209" to-port="0" />
 		<edge from-layer="208" from-port="0" to-layer="209" to-port="1" />
-		<edge from-layer="209" from-port="2" to-layer="211" to-port="0" />
-		<edge from-layer="210" from-port="1" to-layer="211" to-port="1" />
-		<edge from-layer="211" from-port="2" to-layer="214" to-port="0" />
-		<edge from-layer="212" from-port="0" to-layer="213" to-port="0" />
-		<edge from-layer="213" from-port="1" to-layer="214" to-port="1" />
-		<edge from-layer="214" from-port="2" to-layer="217" to-port="0" />
+		<edge from-layer="209" from-port="2" to-layer="210" to-port="1" />
+		<edge from-layer="210" from-port="2" to-layer="213" to-port="0" />
+		<edge from-layer="210" from-port="2" to-layer="241" to-port="0" />
+		<edge from-layer="211" from-port="0" to-layer="213" to-port="1" />
+		<edge from-layer="212" from-port="0" to-layer="213" to-port="2" />
+		<edge from-layer="213" from-port="3" to-layer="214" to-port="0" />
+		<edge from-layer="214" from-port="1" to-layer="223" 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="217" to-port="1" />
-		<edge from-layer="217" from-port="2" to-layer="218" to-port="0" />
-		<edge from-layer="218" from-port="1" to-layer="221" to-port="0" />
-		<edge from-layer="219" from-port="0" to-layer="220" to-port="0" />
-		<edge from-layer="220" from-port="1" to-layer="221" to-port="1" />
-		<edge from-layer="221" from-port="2" to-layer="224" to-port="0" />
-		<edge from-layer="222" from-port="0" to-layer="223" to-port="0" />
-		<edge from-layer="223" from-port="1" to-layer="224" to-port="1" />
-		<edge from-layer="224" from-port="2" to-layer="225" to-port="1" />
-		<edge from-layer="225" from-port="2" to-layer="264" to-port="0" />
-		<edge from-layer="225" from-port="2" to-layer="230" to-port="0" />
-		<edge from-layer="225" from-port="2" to-layer="227" to-port="0" />
-		<edge from-layer="226" from-port="0" to-layer="227" to-port="1" />
-		<edge from-layer="227" from-port="2" to-layer="229" to-port="0" />
-		<edge from-layer="228" from-port="0" to-layer="229" to-port="1" />
-		<edge from-layer="229" from-port="2" to-layer="231" to-port="0" />
-		<edge from-layer="230" from-port="1" to-layer="231" to-port="1" />
-		<edge from-layer="231" from-port="2" to-layer="234" to-port="0" />
+		<edge from-layer="216" from-port="1" to-layer="219" to-port="0" />
+		<edge from-layer="217" from-port="0" to-layer="218" to-port="0" />
+		<edge from-layer="218" from-port="1" to-layer="219" to-port="1" />
+		<edge from-layer="219" from-port="2" to-layer="221" to-port="0" />
+		<edge from-layer="220" from-port="0" to-layer="221" to-port="1" />
+		<edge from-layer="221" from-port="2" to-layer="222" to-port="0" />
+		<edge from-layer="222" from-port="1" to-layer="223" to-port="1" />
+		<edge from-layer="223" from-port="2" to-layer="225" to-port="0" />
+		<edge from-layer="224" from-port="0" to-layer="225" to-port="1" />
+		<edge from-layer="225" from-port="2" to-layer="228" to-port="0" />
+		<edge from-layer="226" from-port="0" to-layer="228" to-port="1" />
+		<edge from-layer="227" from-port="0" to-layer="228" to-port="2" />
+		<edge from-layer="228" from-port="3" to-layer="229" to-port="0" />
+		<edge from-layer="229" from-port="1" to-layer="238" to-port="0" />
+		<edge from-layer="230" from-port="0" to-layer="231" to-port="0" />
+		<edge from-layer="231" from-port="1" to-layer="234" to-port="0" />
 		<edge from-layer="232" from-port="0" to-layer="233" to-port="0" />
 		<edge from-layer="233" from-port="1" to-layer="234" to-port="1" />
-		<edge from-layer="234" from-port="2" to-layer="237" to-port="0" />
-		<edge from-layer="235" from-port="0" to-layer="236" to-port="0" />
-		<edge from-layer="236" from-port="1" to-layer="237" to-port="1" />
-		<edge from-layer="237" from-port="2" to-layer="238" to-port="0" />
-		<edge from-layer="238" from-port="1" to-layer="241" to-port="0" />
-		<edge from-layer="239" from-port="0" to-layer="240" to-port="0" />
-		<edge from-layer="240" from-port="1" to-layer="241" to-port="1" />
-		<edge from-layer="241" from-port="2" to-layer="244" to-port="0" />
+		<edge from-layer="234" from-port="2" to-layer="236" to-port="0" />
+		<edge from-layer="235" from-port="0" to-layer="236" to-port="1" />
+		<edge from-layer="236" from-port="2" to-layer="237" to-port="0" />
+		<edge from-layer="237" from-port="1" to-layer="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="241" to-port="1" />
+		<edge from-layer="241" from-port="2" to-layer="250" to-port="0" />
 		<edge from-layer="242" from-port="0" to-layer="243" to-port="0" />
-		<edge from-layer="243" from-port="1" to-layer="244" to-port="1" />
-		<edge from-layer="244" from-port="2" to-layer="246" to-port="0" />
-		<edge from-layer="244" from-port="2" to-layer="249" to-port="0" />
-		<edge from-layer="245" from-port="0" to-layer="246" to-port="1" />
+		<edge from-layer="243" from-port="1" to-layer="246" to-port="0" />
+		<edge from-layer="244" from-port="0" to-layer="245" to-port="0" />
+		<edge from-layer="245" from-port="1" to-layer="246" to-port="1" />
 		<edge from-layer="246" from-port="2" to-layer="248" to-port="0" />
 		<edge from-layer="247" from-port="0" to-layer="248" to-port="1" />
-		<edge from-layer="248" from-port="2" to-layer="250" to-port="0" />
+		<edge from-layer="248" from-port="2" to-layer="249" to-port="0" />
 		<edge from-layer="249" from-port="1" to-layer="250" to-port="1" />
-		<edge from-layer="250" from-port="2" to-layer="253" to-port="0" />
-		<edge from-layer="251" from-port="0" to-layer="252" to-port="0" />
-		<edge from-layer="252" from-port="1" to-layer="253" to-port="1" />
-		<edge from-layer="253" from-port="2" to-layer="256" to-port="0" />
-		<edge from-layer="254" from-port="0" to-layer="255" to-port="0" />
-		<edge from-layer="255" from-port="1" to-layer="256" to-port="1" />
-		<edge from-layer="256" from-port="2" to-layer="257" to-port="0" />
-		<edge from-layer="257" from-port="1" to-layer="260" to-port="0" />
-		<edge from-layer="258" from-port="0" to-layer="259" to-port="0" />
-		<edge from-layer="259" from-port="1" to-layer="260" to-port="1" />
-		<edge from-layer="260" from-port="2" to-layer="263" to-port="0" />
-		<edge from-layer="261" from-port="0" to-layer="262" to-port="0" />
-		<edge from-layer="262" from-port="1" to-layer="263" to-port="1" />
-		<edge from-layer="263" from-port="2" to-layer="264" to-port="1" />
-		<edge from-layer="264" from-port="2" to-layer="267" to-port="0" />
-		<edge from-layer="265" from-port="0" to-layer="266" to-port="0" />
-		<edge from-layer="266" from-port="1" to-layer="267" 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="255" to-port="0" />
+		<edge from-layer="252" from-port="2" to-layer="283" to-port="0" />
+		<edge from-layer="253" from-port="0" to-layer="255" to-port="1" />
+		<edge from-layer="254" from-port="0" to-layer="255" to-port="2" />
+		<edge from-layer="255" from-port="3" to-layer="256" to-port="0" />
+		<edge from-layer="256" from-port="1" to-layer="265" to-port="0" />
+		<edge from-layer="257" from-port="0" to-layer="258" to-port="0" />
+		<edge from-layer="258" from-port="1" to-layer="261" to-port="0" />
+		<edge from-layer="259" from-port="0" to-layer="260" to-port="0" />
+		<edge from-layer="260" from-port="1" to-layer="261" to-port="1" />
+		<edge from-layer="261" from-port="2" 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="264" to-port="0" />
+		<edge from-layer="264" from-port="1" to-layer="265" to-port="1" />
+		<edge from-layer="265" from-port="2" to-layer="267" to-port="0" />
+		<edge from-layer="266" from-port="0" to-layer="267" to-port="1" />
 		<edge from-layer="267" from-port="2" to-layer="270" to-port="0" />
-		<edge from-layer="268" from-port="0" to-layer="269" to-port="0" />
-		<edge from-layer="269" from-port="1" 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="275" to-port="0" />
-		<edge from-layer="270" from-port="2" to-layer="309" 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="268" from-port="0" to-layer="270" to-port="1" />
+		<edge from-layer="269" from-port="0" to-layer="270" to-port="2" />
+		<edge from-layer="270" from-port="3" to-layer="271" to-port="0" />
+		<edge from-layer="271" from-port="1" to-layer="280" to-port="0" />
+		<edge from-layer="272" from-port="0" to-layer="273" to-port="0" />
+		<edge from-layer="273" from-port="1" to-layer="276" to-port="0" />
+		<edge from-layer="274" from-port="0" to-layer="275" to-port="0" />
 		<edge from-layer="275" from-port="1" to-layer="276" to-port="1" />
-		<edge from-layer="276" from-port="2" to-layer="279" to-port="0" />
-		<edge from-layer="277" from-port="0" to-layer="278" to-port="0" />
-		<edge from-layer="278" from-port="1" to-layer="279" to-port="1" />
-		<edge from-layer="279" from-port="2" to-layer="282" to-port="0" />
-		<edge from-layer="280" from-port="0" to-layer="281" to-port="0" />
-		<edge from-layer="281" from-port="1" 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="286" to-port="0" />
-		<edge from-layer="284" from-port="0" to-layer="285" to-port="0" />
-		<edge from-layer="285" from-port="1" to-layer="286" to-port="1" />
-		<edge from-layer="286" from-port="2" to-layer="289" to-port="0" />
-		<edge from-layer="287" from-port="0" to-layer="288" to-port="0" />
-		<edge from-layer="288" from-port="1" to-layer="289" to-port="1" />
-		<edge from-layer="289" from-port="2" to-layer="291" to-port="0" />
-		<edge from-layer="289" from-port="2" to-layer="294" to-port="0" />
-		<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
-		<edge from-layer="291" from-port="2" to-layer="293" to-port="0" />
-		<edge from-layer="292" from-port="0" to-layer="293" to-port="1" />
-		<edge from-layer="293" from-port="2" to-layer="295" to-port="0" />
-		<edge from-layer="294" from-port="1" to-layer="295" to-port="1" />
-		<edge from-layer="295" from-port="2" to-layer="298" to-port="0" />
-		<edge from-layer="296" from-port="0" to-layer="297" to-port="0" />
-		<edge from-layer="297" from-port="1" to-layer="298" to-port="1" />
+		<edge from-layer="276" from-port="2" to-layer="278" to-port="0" />
+		<edge from-layer="277" from-port="0" to-layer="278" to-port="1" />
+		<edge from-layer="278" from-port="2" to-layer="279" to-port="0" />
+		<edge from-layer="279" from-port="1" 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="1" />
+		<edge from-layer="283" from-port="2" to-layer="286" to-port="0" />
+		<edge from-layer="283" from-port="2" to-layer="314" to-port="0" />
+		<edge from-layer="284" from-port="0" to-layer="286" to-port="1" />
+		<edge from-layer="285" from-port="0" to-layer="286" to-port="2" />
+		<edge from-layer="286" from-port="3" to-layer="287" to-port="0" />
+		<edge from-layer="287" from-port="1" to-layer="296" 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="292" to-port="0" />
+		<edge from-layer="290" from-port="0" to-layer="291" to-port="0" />
+		<edge from-layer="291" from-port="1" to-layer="292" to-port="1" />
+		<edge from-layer="292" from-port="2" to-layer="294" to-port="0" />
+		<edge from-layer="293" from-port="0" to-layer="294" to-port="1" />
+		<edge from-layer="294" from-port="2" to-layer="295" to-port="0" />
+		<edge from-layer="295" from-port="1" to-layer="296" to-port="1" />
+		<edge from-layer="296" from-port="2" to-layer="298" to-port="0" />
+		<edge from-layer="297" from-port="0" to-layer="298" to-port="1" />
 		<edge from-layer="298" from-port="2" to-layer="301" to-port="0" />
-		<edge from-layer="299" from-port="0" to-layer="300" to-port="0" />
-		<edge from-layer="300" from-port="1" to-layer="301" to-port="1" />
-		<edge from-layer="301" from-port="2" to-layer="302" to-port="0" />
-		<edge from-layer="302" from-port="1" to-layer="305" to-port="0" />
+		<edge from-layer="299" from-port="0" to-layer="301" to-port="1" />
+		<edge from-layer="300" from-port="0" to-layer="301" to-port="2" />
+		<edge from-layer="301" from-port="3" to-layer="302" to-port="0" />
+		<edge from-layer="302" from-port="1" to-layer="311" to-port="0" />
 		<edge from-layer="303" from-port="0" to-layer="304" to-port="0" />
-		<edge from-layer="304" from-port="1" to-layer="305" to-port="1" />
-		<edge from-layer="305" from-port="2" to-layer="308" to-port="0" />
-		<edge from-layer="306" from-port="0" to-layer="307" to-port="0" />
-		<edge from-layer="307" from-port="1" to-layer="308" to-port="1" />
-		<edge from-layer="308" from-port="2" to-layer="309" to-port="1" />
-		<edge from-layer="309" from-port="2" to-layer="311" to-port="0" />
-		<edge from-layer="309" from-port="2" to-layer="348" to-port="0" />
-		<edge from-layer="309" from-port="2" to-layer="314" to-port="0" />
-		<edge from-layer="310" from-port="0" to-layer="311" to-port="1" />
+		<edge from-layer="304" from-port="1" to-layer="307" 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="307" to-port="1" />
+		<edge from-layer="307" from-port="2" to-layer="309" to-port="0" />
+		<edge from-layer="308" from-port="0" to-layer="309" to-port="1" />
+		<edge from-layer="309" from-port="2" to-layer="310" to-port="0" />
+		<edge from-layer="310" from-port="1" to-layer="311" to-port="1" />
 		<edge from-layer="311" from-port="2" to-layer="313" to-port="0" />
 		<edge from-layer="312" from-port="0" to-layer="313" to-port="1" />
-		<edge from-layer="313" from-port="2" to-layer="315" to-port="0" />
-		<edge from-layer="314" from-port="1" to-layer="315" to-port="1" />
-		<edge from-layer="315" from-port="2" to-layer="318" to-port="0" />
-		<edge from-layer="316" from-port="0" to-layer="317" to-port="0" />
-		<edge from-layer="317" from-port="1" to-layer="318" to-port="1" />
-		<edge from-layer="318" from-port="2" to-layer="321" to-port="0" />
+		<edge from-layer="313" from-port="2" to-layer="314" to-port="1" />
+		<edge from-layer="314" from-port="2" to-layer="317" to-port="0" />
+		<edge from-layer="314" from-port="2" to-layer="345" to-port="0" />
+		<edge from-layer="315" from-port="0" to-layer="317" to-port="1" />
+		<edge from-layer="316" from-port="0" to-layer="317" to-port="2" />
+		<edge from-layer="317" from-port="3" to-layer="318" to-port="0" />
+		<edge from-layer="318" from-port="1" to-layer="327" 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="321" to-port="1" />
-		<edge from-layer="321" from-port="2" to-layer="322" to-port="0" />
-		<edge from-layer="322" from-port="1" to-layer="325" to-port="0" />
-		<edge from-layer="323" from-port="0" to-layer="324" to-port="0" />
-		<edge from-layer="324" from-port="1" to-layer="325" to-port="1" />
-		<edge from-layer="325" from-port="2" to-layer="328" to-port="0" />
-		<edge from-layer="326" from-port="0" to-layer="327" to-port="0" />
-		<edge from-layer="327" from-port="1" to-layer="328" to-port="1" />
-		<edge from-layer="328" from-port="2" to-layer="333" to-port="0" />
-		<edge from-layer="328" from-port="2" to-layer="330" to-port="0" />
-		<edge from-layer="329" from-port="0" to-layer="330" to-port="1" />
-		<edge from-layer="330" from-port="2" to-layer="332" to-port="0" />
-		<edge from-layer="331" from-port="0" to-layer="332" to-port="1" />
-		<edge from-layer="332" from-port="2" to-layer="334" to-port="0" />
-		<edge from-layer="333" from-port="1" to-layer="334" to-port="1" />
-		<edge from-layer="334" from-port="2" to-layer="337" to-port="0" />
-		<edge from-layer="335" from-port="0" to-layer="336" to-port="0" />
-		<edge from-layer="336" from-port="1" to-layer="337" to-port="1" />
-		<edge from-layer="337" from-port="2" to-layer="340" to-port="0" />
-		<edge from-layer="338" from-port="0" to-layer="339" to-port="0" />
-		<edge from-layer="339" from-port="1" to-layer="340" to-port="1" />
+		<edge from-layer="320" from-port="1" to-layer="323" to-port="0" />
+		<edge from-layer="321" from-port="0" to-layer="322" to-port="0" />
+		<edge from-layer="322" from-port="1" to-layer="323" to-port="1" />
+		<edge from-layer="323" from-port="2" to-layer="325" to-port="0" />
+		<edge from-layer="324" from-port="0" to-layer="325" to-port="1" />
+		<edge from-layer="325" from-port="2" to-layer="326" to-port="0" />
+		<edge from-layer="326" from-port="1" to-layer="327" to-port="1" />
+		<edge from-layer="327" from-port="2" to-layer="329" to-port="0" />
+		<edge from-layer="328" from-port="0" to-layer="329" to-port="1" />
+		<edge from-layer="329" from-port="2" to-layer="332" to-port="0" />
+		<edge from-layer="330" from-port="0" to-layer="332" to-port="1" />
+		<edge from-layer="331" from-port="0" to-layer="332" to-port="2" />
+		<edge from-layer="332" from-port="3" to-layer="333" to-port="0" />
+		<edge from-layer="333" from-port="1" to-layer="342" to-port="0" />
+		<edge from-layer="334" from-port="0" to-layer="335" to-port="0" />
+		<edge from-layer="335" from-port="1" to-layer="338" to-port="0" />
+		<edge from-layer="336" from-port="0" to-layer="337" to-port="0" />
+		<edge from-layer="337" from-port="1" to-layer="338" to-port="1" />
+		<edge from-layer="338" from-port="2" to-layer="340" to-port="0" />
+		<edge from-layer="339" from-port="0" to-layer="340" to-port="1" />
 		<edge from-layer="340" from-port="2" to-layer="341" to-port="0" />
-		<edge from-layer="341" from-port="1" to-layer="344" to-port="0" />
-		<edge from-layer="342" from-port="0" to-layer="343" to-port="0" />
-		<edge from-layer="343" from-port="1" to-layer="344" to-port="1" />
-		<edge from-layer="344" from-port="2" to-layer="347" to-port="0" />
-		<edge from-layer="345" from-port="0" to-layer="346" to-port="0" />
-		<edge from-layer="346" from-port="1" to-layer="347" to-port="1" />
-		<edge from-layer="347" from-port="2" to-layer="348" to-port="1" />
-		<edge from-layer="348" from-port="2" to-layer="350" to-port="0" />
-		<edge from-layer="348" from-port="2" to-layer="387" to-port="0" />
-		<edge from-layer="348" from-port="2" to-layer="353" to-port="0" />
-		<edge from-layer="349" from-port="0" to-layer="350" to-port="1" />
-		<edge from-layer="350" from-port="2" to-layer="352" to-port="0" />
-		<edge from-layer="351" from-port="0" to-layer="352" to-port="1" />
-		<edge from-layer="352" from-port="2" to-layer="354" to-port="0" />
-		<edge from-layer="353" from-port="1" to-layer="354" to-port="1" />
-		<edge from-layer="354" from-port="2" to-layer="357" to-port="0" />
+		<edge from-layer="341" from-port="1" 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="1" />
+		<edge from-layer="345" from-port="2" to-layer="420" to-port="1" />
+		<edge from-layer="345" from-port="2" to-layer="418" to-port="0" />
+		<edge from-layer="345" from-port="2" 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="351" to-port="0" />
+		<edge from-layer="350" from-port="0" to-layer="351" to-port="1" />
+		<edge from-layer="351" from-port="2" to-layer="354" to-port="0" />
+		<edge from-layer="352" from-port="0" to-layer="354" to-port="1" />
+		<edge from-layer="353" from-port="0" to-layer="354" to-port="2" />
+		<edge from-layer="354" from-port="3" to-layer="363" to-port="0" />
+		<edge from-layer="354" from-port="3" to-layer="393" to-port="0" />
+		<edge from-layer="354" from-port="3" to-layer="378" to-port="0" />
 		<edge from-layer="355" from-port="0" 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="360" to-port="0" />
-		<edge from-layer="358" from-port="0" to-layer="359" to-port="0" />
-		<edge from-layer="359" from-port="1" to-layer="360" to-port="1" />
-		<edge from-layer="360" from-port="2" to-layer="361" to-port="0" />
-		<edge from-layer="361" from-port="1" to-layer="364" to-port="0" />
-		<edge from-layer="362" from-port="0" to-layer="363" to-port="0" />
-		<edge from-layer="363" from-port="1" to-layer="364" to-port="1" />
-		<edge from-layer="364" from-port="2" to-layer="367" to-port="0" />
-		<edge from-layer="365" from-port="0" to-layer="366" to-port="0" />
-		<edge from-layer="366" from-port="1" to-layer="367" to-port="1" />
+		<edge from-layer="356" from-port="1" to-layer="359" to-port="0" />
+		<edge from-layer="357" from-port="0" to-layer="358" to-port="0" />
+		<edge from-layer="358" from-port="1" to-layer="359" to-port="1" />
+		<edge from-layer="359" from-port="2" to-layer="361" to-port="0" />
+		<edge from-layer="360" from-port="0" to-layer="361" to-port="1" />
+		<edge from-layer="361" from-port="2" to-layer="362" to-port="0" />
+		<edge from-layer="362" from-port="1" to-layer="363" to-port="1" />
+		<edge from-layer="363" from-port="2" to-layer="365" to-port="0" />
+		<edge from-layer="364" from-port="0" to-layer="365" to-port="1" />
+		<edge from-layer="365" from-port="2" to-layer="367" to-port="0" />
+		<edge from-layer="366" from-port="0" to-layer="367" to-port="1" />
 		<edge from-layer="367" from-port="2" to-layer="369" to-port="0" />
-		<edge from-layer="367" from-port="2" to-layer="372" to-port="0" />
 		<edge from-layer="368" from-port="0" to-layer="369" to-port="1" />
-		<edge from-layer="369" from-port="2" to-layer="371" to-port="0" />
-		<edge from-layer="370" from-port="0" to-layer="371" to-port="1" />
-		<edge from-layer="371" from-port="2" to-layer="373" to-port="0" />
-		<edge from-layer="372" from-port="1" to-layer="373" to-port="1" />
-		<edge from-layer="373" from-port="2" to-layer="376" to-port="0" />
-		<edge from-layer="374" from-port="0" to-layer="375" to-port="0" />
-		<edge from-layer="375" from-port="1" to-layer="376" to-port="1" />
-		<edge from-layer="376" from-port="2" to-layer="379" to-port="0" />
-		<edge from-layer="377" from-port="0" to-layer="378" to-port="0" />
-		<edge from-layer="378" from-port="1" to-layer="379" to-port="1" />
-		<edge from-layer="379" from-port="2" to-layer="380" to-port="0" />
-		<edge from-layer="380" from-port="1" to-layer="383" to-port="0" />
-		<edge from-layer="381" from-port="0" to-layer="382" to-port="0" />
-		<edge from-layer="382" from-port="1" to-layer="383" to-port="1" />
-		<edge from-layer="383" from-port="2" to-layer="386" to-port="0" />
-		<edge from-layer="384" from-port="0" to-layer="385" to-port="0" />
-		<edge from-layer="385" from-port="1" to-layer="386" to-port="1" />
-		<edge from-layer="386" from-port="2" to-layer="387" to-port="1" />
-		<edge from-layer="387" from-port="2" to-layer="388" to-port="0" />
-		<edge from-layer="387" from-port="2" to-layer="403" to-port="0" />
-		<edge from-layer="387" from-port="2" to-layer="479" to-port="1" />
-		<edge from-layer="388" from-port="1" to-layer="391" to-port="0" />
-		<edge from-layer="388" from-port="1" to-layer="395" to-port="0" />
-		<edge from-layer="388" from-port="1" to-layer="398" to-port="0" />
-		<edge from-layer="389" from-port="0" to-layer="391" to-port="1" />
-		<edge from-layer="390" from-port="0" to-layer="391" to-port="2" />
-		<edge from-layer="391" from-port="3" to-layer="402" to-port="0" />
-		<edge from-layer="392" from-port="0" to-layer="477" to-port="1" />
-		<edge from-layer="392" from-port="0" to-layer="402" to-port="1" />
-		<edge from-layer="393" from-port="0" to-layer="395" to-port="1" />
-		<edge from-layer="393" from-port="0" to-layer="440" to-port="1" />
-		<edge from-layer="394" from-port="0" to-layer="395" to-port="2" />
-		<edge from-layer="395" from-port="3" to-layer="474" to-port="0" />
-		<edge from-layer="395" from-port="3" to-layer="399" to-port="0" />
-		<edge from-layer="396" from-port="0" to-layer="398" to-port="1" />
-		<edge from-layer="397" from-port="0" to-layer="398" to-port="2" />
-		<edge from-layer="398" from-port="3" to-layer="399" to-port="1" />
-		<edge from-layer="398" from-port="3" to-layer="476" to-port="0" />
-		<edge from-layer="399" from-port="2" to-layer="401" to-port="0" />
-		<edge from-layer="400" from-port="0" to-layer="401" to-port="1" />
-		<edge from-layer="401" from-port="2" to-layer="402" to-port="2" />
-		<edge from-layer="402" from-port="3" to-layer="403" to-port="1" />
-		<edge from-layer="403" from-port="2" to-layer="405" to-port="0" />
-		<edge from-layer="404" from-port="0" to-layer="405" to-port="1" />
-		<edge from-layer="405" from-port="2" to-layer="407" to-port="0" />
-		<edge from-layer="405" from-port="2" to-layer="426" to-port="0" />
-		<edge from-layer="406" from-port="0" to-layer="407" to-port="1" />
-		<edge from-layer="407" from-port="2" to-layer="409" to-port="0" />
-		<edge from-layer="407" from-port="2" to-layer="412" to-port="0" />
-		<edge from-layer="408" from-port="0" to-layer="409" to-port="1" />
+		<edge from-layer="369" from-port="2" to-layer="400" to-port="0" />
+		<edge from-layer="370" from-port="0" to-layer="371" to-port="0" />
+		<edge from-layer="371" from-port="1" to-layer="374" to-port="0" />
+		<edge from-layer="372" from-port="0" 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="378" to-port="1" />
+		<edge from-layer="378" from-port="2" to-layer="380" to-port="0" />
+		<edge from-layer="379" from-port="0" to-layer="380" to-port="1" />
+		<edge from-layer="380" from-port="2" to-layer="382" to-port="0" />
+		<edge from-layer="381" from-port="0" to-layer="382" to-port="1" />
+		<edge from-layer="382" from-port="2" to-layer="384" to-port="0" />
+		<edge from-layer="383" from-port="0" to-layer="384" to-port="1" />
+		<edge from-layer="384" from-port="2" to-layer="400" to-port="1" />
+		<edge from-layer="385" from-port="0" to-layer="386" to-port="0" />
+		<edge from-layer="386" from-port="1" to-layer="389" to-port="0" />
+		<edge from-layer="387" from-port="0" to-layer="388" to-port="0" />
+		<edge from-layer="388" from-port="1" to-layer="389" to-port="1" />
+		<edge from-layer="389" from-port="2" to-layer="391" to-port="0" />
+		<edge from-layer="390" from-port="0" to-layer="391" to-port="1" />
+		<edge from-layer="391" from-port="2" to-layer="392" to-port="0" />
+		<edge from-layer="392" from-port="1" to-layer="393" to-port="1" />
+		<edge from-layer="393" from-port="2" to-layer="395" to-port="0" />
+		<edge from-layer="394" from-port="0" to-layer="395" to-port="1" />
+		<edge from-layer="395" from-port="2" to-layer="397" to-port="0" />
+		<edge from-layer="396" from-port="0" to-layer="397" to-port="1" />
+		<edge from-layer="397" from-port="2" to-layer="399" to-port="0" />
+		<edge from-layer="398" from-port="0" to-layer="399" to-port="1" />
+		<edge from-layer="399" from-port="2" to-layer="400" to-port="2" />
+		<edge from-layer="400" from-port="3" to-layer="402" to-port="0" />
+		<edge from-layer="401" from-port="0" to-layer="402" to-port="1" />
+		<edge from-layer="402" from-port="2" to-layer="404" to-port="0" />
+		<edge from-layer="403" from-port="0" to-layer="404" to-port="1" />
+		<edge from-layer="404" from-port="2" to-layer="413" to-port="0" />
+		<edge from-layer="405" from-port="0" to-layer="406" to-port="0" />
+		<edge from-layer="406" from-port="1" to-layer="409" to-port="0" />
+		<edge from-layer="407" from-port="0" to-layer="408" to-port="0" />
+		<edge from-layer="408" from-port="1" to-layer="409" to-port="1" />
 		<edge from-layer="409" from-port="2" to-layer="411" to-port="0" />
 		<edge from-layer="410" from-port="0" to-layer="411" to-port="1" />
-		<edge from-layer="411" from-port="2" to-layer="413" to-port="0" />
+		<edge from-layer="411" from-port="2" to-layer="412" to-port="0" />
 		<edge from-layer="412" from-port="1" to-layer="413" to-port="1" />
-		<edge from-layer="413" from-port="2" to-layer="416" to-port="0" />
-		<edge from-layer="414" from-port="0" to-layer="415" to-port="0" />
-		<edge from-layer="415" from-port="1" to-layer="416" to-port="1" />
-		<edge from-layer="416" from-port="2" to-layer="419" to-port="0" />
-		<edge from-layer="417" from-port="0" to-layer="418" to-port="0" />
+		<edge from-layer="413" from-port="2" to-layer="415" to-port="0" />
+		<edge from-layer="414" from-port="0" to-layer="415" to-port="1" />
+		<edge from-layer="415" from-port="2" to-layer="417" to-port="0" />
+		<edge from-layer="416" from-port="0" to-layer="417" to-port="1" />
+		<edge from-layer="417" from-port="2" to-layer="419" to-port="0" />
 		<edge from-layer="418" from-port="1" to-layer="419" to-port="1" />
-		<edge from-layer="419" from-port="2" to-layer="422" to-port="0" />
-		<edge from-layer="419" from-port="2" to-layer="453" to-port="0" />
-		<edge from-layer="419" from-port="2" to-layer="434" to-port="0" />
-		<edge from-layer="420" from-port="0" to-layer="421" to-port="0" />
-		<edge from-layer="421" from-port="1" to-layer="422" to-port="1" />
-		<edge from-layer="422" from-port="2" to-layer="425" to-port="0" />
-		<edge from-layer="423" from-port="0" to-layer="424" to-port="0" />
-		<edge from-layer="424" from-port="1" to-layer="425" to-port="1" />
-		<edge from-layer="425" from-port="2" to-layer="445" to-port="0" />
+		<edge from-layer="419" from-port="2" to-layer="420" to-port="0" />
+		<edge from-layer="420" from-port="2" to-layer="423" to-port="0" />
+		<edge from-layer="420" from-port="2" to-layer="451" to-port="0" />
+		<edge from-layer="421" from-port="0" to-layer="423" to-port="1" />
+		<edge from-layer="422" from-port="0" to-layer="423" to-port="2" />
+		<edge from-layer="423" from-port="3" to-layer="424" to-port="0" />
+		<edge from-layer="424" from-port="1" to-layer="433" to-port="0" />
+		<edge from-layer="425" from-port="0" to-layer="426" to-port="0" />
 		<edge from-layer="426" from-port="1" to-layer="429" to-port="0" />
-		<edge from-layer="427" from-port="0" to-layer="429" to-port="1" />
-		<edge from-layer="428" from-port="0" to-layer="429" to-port="2" />
-		<edge from-layer="429" from-port="3" to-layer="477" to-port="0" />
-		<edge from-layer="429" from-port="3" to-layer="463" to-port="0" />
-		<edge from-layer="429" from-port="3" to-layer="444" to-port="0" />
-		<edge from-layer="430" from-port="0" to-layer="444" to-port="1" />
-		<edge from-layer="430" from-port="0" to-layer="463" to-port="1" />
-		<edge from-layer="431" from-port="0" to-layer="444" to-port="2" />
-		<edge from-layer="432" from-port="0" to-layer="433" to-port="0" />
-		<edge from-layer="433" from-port="1" to-layer="434" to-port="1" />
-		<edge from-layer="434" from-port="2" to-layer="437" to-port="0" />
-		<edge from-layer="435" from-port="0" to-layer="436" to-port="0" />
-		<edge from-layer="436" from-port="1" to-layer="437" to-port="1" />
-		<edge from-layer="437" from-port="2" to-layer="448" to-port="0" />
-		<edge from-layer="437" from-port="2" to-layer="438" to-port="0" />
-		<edge from-layer="438" from-port="1" to-layer="440" to-port="0" />
-		<edge from-layer="439" from-port="0" to-layer="440" to-port="2" />
-		<edge from-layer="440" from-port="3" to-layer="441" to-port="0" />
-		<edge from-layer="441" from-port="1" to-layer="443" to-port="0" />
-		<edge from-layer="442" from-port="0" to-layer="443" to-port="1" />
-		<edge from-layer="443" from-port="2" to-layer="444" to-port="3" />
-		<edge from-layer="443" from-port="2" to-layer="463" to-port="2" />
-		<edge from-layer="444" from-port="4" to-layer="448" to-port="1" />
-		<edge from-layer="444" from-port="4" to-layer="445" to-port="1" />
-		<edge from-layer="444" from-port="4" to-layer="457" to-port="1" />
-		<edge from-layer="445" from-port="2" to-layer="447" to-port="0" />
-		<edge from-layer="446" from-port="0" to-layer="447" to-port="1" />
-		<edge from-layer="447" from-port="2" to-layer="460" to-port="0" />
+		<edge from-layer="427" from-port="0" to-layer="428" to-port="0" />
+		<edge from-layer="428" from-port="1" to-layer="429" to-port="1" />
+		<edge from-layer="429" from-port="2" to-layer="431" to-port="0" />
+		<edge from-layer="430" from-port="0" to-layer="431" to-port="1" />
+		<edge from-layer="431" from-port="2" to-layer="432" to-port="0" />
+		<edge from-layer="432" from-port="1" to-layer="433" to-port="1" />
+		<edge from-layer="433" from-port="2" to-layer="435" to-port="0" />
+		<edge from-layer="434" from-port="0" to-layer="435" to-port="1" />
+		<edge from-layer="435" from-port="2" to-layer="438" to-port="0" />
+		<edge from-layer="436" from-port="0" to-layer="438" to-port="1" />
+		<edge from-layer="437" from-port="0" to-layer="438" to-port="2" />
+		<edge from-layer="438" from-port="3" to-layer="439" to-port="0" />
+		<edge from-layer="439" from-port="1" to-layer="448" to-port="0" />
+		<edge from-layer="440" from-port="0" to-layer="441" to-port="0" />
+		<edge from-layer="441" from-port="1" to-layer="444" to-port="0" />
+		<edge from-layer="442" from-port="0" to-layer="443" to-port="0" />
+		<edge from-layer="443" from-port="1" to-layer="444" to-port="1" />
+		<edge from-layer="444" from-port="2" to-layer="446" to-port="0" />
+		<edge from-layer="445" from-port="0" to-layer="446" to-port="1" />
+		<edge from-layer="446" from-port="2" to-layer="447" to-port="0" />
+		<edge from-layer="447" from-port="1" to-layer="448" to-port="1" />
 		<edge from-layer="448" from-port="2" to-layer="450" to-port="0" />
 		<edge from-layer="449" from-port="0" to-layer="450" to-port="1" />
-		<edge from-layer="450" from-port="2" to-layer="460" to-port="1" />
-		<edge from-layer="451" from-port="0" to-layer="452" to-port="0" />
-		<edge from-layer="452" from-port="1" to-layer="453" to-port="1" />
-		<edge from-layer="453" from-port="2" to-layer="456" to-port="0" />
-		<edge from-layer="454" from-port="0" to-layer="455" to-port="0" />
-		<edge from-layer="455" from-port="1" to-layer="456" to-port="1" />
-		<edge from-layer="456" from-port="2" to-layer="457" to-port="0" />
-		<edge from-layer="457" from-port="2" to-layer="459" to-port="0" />
-		<edge from-layer="458" from-port="0" to-layer="459" to-port="1" />
-		<edge from-layer="459" from-port="2" to-layer="460" to-port="2" />
-		<edge from-layer="460" from-port="3" to-layer="462" to-port="0" />
+		<edge from-layer="450" from-port="2" to-layer="451" to-port="1" />
+		<edge from-layer="451" from-port="2" to-layer="454" to-port="0" />
+		<edge from-layer="452" from-port="0" to-layer="454" to-port="1" />
+		<edge from-layer="453" from-port="0" to-layer="454" to-port="2" />
+		<edge from-layer="454" from-port="3" to-layer="455" to-port="0" />
+		<edge from-layer="455" from-port="1" to-layer="464" to-port="0" />
+		<edge from-layer="456" from-port="0" to-layer="457" to-port="0" />
+		<edge from-layer="457" from-port="1" to-layer="460" to-port="0" />
+		<edge from-layer="458" from-port="0" to-layer="459" to-port="0" />
+		<edge from-layer="459" from-port="1" to-layer="460" to-port="1" />
+		<edge from-layer="460" from-port="2" to-layer="462" to-port="0" />
 		<edge from-layer="461" from-port="0" to-layer="462" to-port="1" />
-		<edge from-layer="462" from-port="2" to-layer="464" to-port="0" />
-		<edge from-layer="463" from-port="3" to-layer="464" to-port="1" />
-		<edge from-layer="464" from-port="2" to-layer="467" to-port="0" />
-		<edge from-layer="465" from-port="0" to-layer="466" to-port="0" />
-		<edge from-layer="466" from-port="1" to-layer="467" to-port="1" />
-		<edge from-layer="467" from-port="2" to-layer="470" to-port="0" />
-		<edge from-layer="468" from-port="0" to-layer="469" to-port="0" />
-		<edge from-layer="469" from-port="1" to-layer="470" to-port="1" />
-		<edge from-layer="470" from-port="2" to-layer="472" to-port="0" />
-		<edge from-layer="471" from-port="0" to-layer="472" to-port="1" />
-		<edge from-layer="472" from-port="2" to-layer="478" to-port="0" />
-		<edge from-layer="473" from-port="0" to-layer="474" to-port="1" />
-		<edge from-layer="474" from-port="2" to-layer="477" to-port="2" />
-		<edge from-layer="475" from-port="0" to-layer="476" to-port="1" />
-		<edge from-layer="476" from-port="2" to-layer="477" to-port="3" />
-		<edge from-layer="477" from-port="4" to-layer="478" to-port="1" />
-		<edge from-layer="478" from-port="2" to-layer="479" to-port="0" />
-		<edge from-layer="479" from-port="2" to-layer="481" to-port="0" />
-		<edge from-layer="479" from-port="2" to-layer="484" to-port="0" />
-		<edge from-layer="479" from-port="2" to-layer="518" to-port="0" />
-		<edge from-layer="480" from-port="0" to-layer="481" to-port="1" />
-		<edge from-layer="481" from-port="2" to-layer="483" to-port="0" />
-		<edge from-layer="482" from-port="0" to-layer="483" to-port="1" />
-		<edge from-layer="483" from-port="2" to-layer="485" to-port="0" />
-		<edge from-layer="484" from-port="1" to-layer="485" to-port="1" />
-		<edge from-layer="485" from-port="2" to-layer="488" to-port="0" />
-		<edge from-layer="486" from-port="0" to-layer="487" to-port="0" />
-		<edge from-layer="487" from-port="1" to-layer="488" to-port="1" />
-		<edge from-layer="488" from-port="2" to-layer="491" to-port="0" />
-		<edge from-layer="489" from-port="0" to-layer="490" to-port="0" />
-		<edge from-layer="490" from-port="1" to-layer="491" to-port="1" />
-		<edge from-layer="491" from-port="2" to-layer="492" to-port="0" />
-		<edge from-layer="492" from-port="1" to-layer="495" to-port="0" />
-		<edge from-layer="493" from-port="0" to-layer="494" to-port="0" />
-		<edge from-layer="494" from-port="1" to-layer="495" to-port="1" />
-		<edge from-layer="495" from-port="2" to-layer="498" to-port="0" />
-		<edge from-layer="496" from-port="0" to-layer="497" to-port="0" />
-		<edge from-layer="497" from-port="1" to-layer="498" to-port="1" />
-		<edge from-layer="498" from-port="2" to-layer="500" to-port="0" />
-		<edge from-layer="498" from-port="2" to-layer="503" to-port="0" />
-		<edge from-layer="499" from-port="0" to-layer="500" to-port="1" />
-		<edge from-layer="500" from-port="2" to-layer="502" to-port="0" />
-		<edge from-layer="501" from-port="0" to-layer="502" to-port="1" />
-		<edge from-layer="502" from-port="2" to-layer="504" to-port="0" />
-		<edge from-layer="503" from-port="1" to-layer="504" to-port="1" />
-		<edge from-layer="504" from-port="2" to-layer="507" to-port="0" />
-		<edge from-layer="505" from-port="0" to-layer="506" to-port="0" />
-		<edge from-layer="506" from-port="1" to-layer="507" to-port="1" />
-		<edge from-layer="507" from-port="2" to-layer="510" to-port="0" />
-		<edge from-layer="508" from-port="0" to-layer="509" to-port="0" />
-		<edge from-layer="509" from-port="1" to-layer="510" to-port="1" />
-		<edge from-layer="510" from-port="2" to-layer="511" to-port="0" />
-		<edge from-layer="511" from-port="1" to-layer="514" to-port="0" />
-		<edge from-layer="512" from-port="0" to-layer="513" to-port="0" />
-		<edge from-layer="513" from-port="1" to-layer="514" to-port="1" />
-		<edge from-layer="514" from-port="2" to-layer="517" to-port="0" />
-		<edge from-layer="515" from-port="0" to-layer="516" to-port="0" />
-		<edge from-layer="516" from-port="1" to-layer="517" to-port="1" />
-		<edge from-layer="517" from-port="2" to-layer="518" to-port="1" />
-		<edge from-layer="518" from-port="2" to-layer="520" to-port="0" />
-		<edge from-layer="518" from-port="2" to-layer="523" to-port="0" />
-		<edge from-layer="519" from-port="0" to-layer="520" to-port="1" />
-		<edge from-layer="520" from-port="2" to-layer="522" to-port="0" />
-		<edge from-layer="521" from-port="0" to-layer="522" to-port="1" />
-		<edge from-layer="522" from-port="2" to-layer="524" to-port="0" />
-		<edge from-layer="523" from-port="1" to-layer="524" to-port="1" />
-		<edge from-layer="524" from-port="2" to-layer="527" to-port="0" />
-		<edge from-layer="525" from-port="0" to-layer="526" to-port="0" />
-		<edge from-layer="526" from-port="1" to-layer="527" to-port="1" />
-		<edge from-layer="527" from-port="2" to-layer="530" to-port="0" />
-		<edge from-layer="528" from-port="0" to-layer="529" to-port="0" />
-		<edge from-layer="529" from-port="1" to-layer="530" to-port="1" />
-		<edge from-layer="530" from-port="2" to-layer="531" to-port="0" />
-		<edge from-layer="531" from-port="1" to-layer="534" to-port="0" />
-		<edge from-layer="532" from-port="0" to-layer="533" to-port="0" />
-		<edge from-layer="533" from-port="1" to-layer="534" to-port="1" />
-		<edge from-layer="534" from-port="2" to-layer="537" to-port="0" />
-		<edge from-layer="535" from-port="0" to-layer="536" to-port="0" />
-		<edge from-layer="536" from-port="1" to-layer="537" to-port="1" />
-		<edge from-layer="537" from-port="2" to-layer="540" to-port="0" />
-		<edge from-layer="538" from-port="0" to-layer="539" to-port="0" />
-		<edge from-layer="539" from-port="1" to-layer="540" to-port="1" />
-		<edge from-layer="540" from-port="2" to-layer="543" to-port="0" />
-		<edge from-layer="541" from-port="0" to-layer="542" to-port="0" />
-		<edge from-layer="542" from-port="1" to-layer="543" to-port="1" />
-		<edge from-layer="543" from-port="2" to-layer="545" to-port="0" />
-		<edge from-layer="543" from-port="2" to-layer="558" to-port="0" />
-		<edge from-layer="544" from-port="0" to-layer="547" to-port="1" />
-		<edge from-layer="544" from-port="0" to-layer="558" to-port="1" />
-		<edge from-layer="545" from-port="1" to-layer="547" to-port="0" />
-		<edge from-layer="546" from-port="0" to-layer="551" to-port="1" />
-		<edge from-layer="546" from-port="0" to-layer="547" to-port="2" />
-		<edge from-layer="547" from-port="3" to-layer="550" to-port="0" />
-		<edge from-layer="547" from-port="3" to-layer="549" to-port="0" />
-		<edge from-layer="548" from-port="0" to-layer="549" to-port="1" />
-		<edge from-layer="548" from-port="0" to-layer="550" to-port="1" />
-		<edge from-layer="549" from-port="2" to-layer="553" to-port="0" />
-		<edge from-layer="550" from-port="2" to-layer="551" to-port="0" />
-		<edge from-layer="551" from-port="2" to-layer="552" to-port="0" />
-		<edge from-layer="552" from-port="1" to-layer="553" to-port="1" />
-		<edge from-layer="553" from-port="2" to-layer="555" to-port="0" />
-		<edge from-layer="554" from-port="0" to-layer="555" to-port="1" />
-		<edge from-layer="555" from-port="2" to-layer="557" to-port="0" />
-		<edge from-layer="556" from-port="0" to-layer="557" to-port="1" />
-		<edge from-layer="557" from-port="2" to-layer="558" to-port="2" />
-		<edge from-layer="558" from-port="4" to-layer="559" to-port="0" />
-		<edge from-layer="558" from-port="3" to-layer="564" to-port="0" />
-		<edge from-layer="558" from-port="3" to-layer="600" to-port="0" />
-		<edge from-layer="559" from-port="1" to-layer="562" to-port="0" />
-		<edge from-layer="560" from-port="0" to-layer="561" to-port="0" />
-		<edge from-layer="561" from-port="1" to-layer="562" to-port="1" />
-		<edge from-layer="562" from-port="2" to-layer="563" to-port="0" />
-		<edge from-layer="563" from-port="1" to-layer="599" to-port="0" />
-		<edge from-layer="564" from-port="1" to-layer="567" to-port="0" />
-		<edge from-layer="564" from-port="1" to-layer="572" to-port="0" />
-		<edge from-layer="564" from-port="1" to-layer="580" to-port="0" />
-		<edge from-layer="564" from-port="1" to-layer="576" to-port="0" />
-		<edge from-layer="565" from-port="0" to-layer="567" to-port="1" />
-		<edge from-layer="566" from-port="0" to-layer="567" to-port="2" />
-		<edge from-layer="567" from-port="3" to-layer="569" to-port="0" />
-		<edge from-layer="568" from-port="0" to-layer="573" to-port="1" />
-		<edge from-layer="568" from-port="0" to-layer="577" to-port="1" />
-		<edge from-layer="568" from-port="0" to-layer="581" to-port="1" />
-		<edge from-layer="568" from-port="0" to-layer="569" to-port="1" />
-		<edge from-layer="569" from-port="2" to-layer="582" to-port="0" />
-		<edge from-layer="570" from-port="0" to-layer="572" to-port="1" />
-		<edge from-layer="571" from-port="0" to-layer="572" to-port="2" />
-		<edge from-layer="572" from-port="3" to-layer="573" to-port="0" />
-		<edge from-layer="573" from-port="2" to-layer="582" to-port="1" />
-		<edge from-layer="574" from-port="0" to-layer="576" to-port="1" />
-		<edge from-layer="575" from-port="0" to-layer="576" to-port="2" />
-		<edge from-layer="576" from-port="3" to-layer="577" to-port="0" />
-		<edge from-layer="577" from-port="2" to-layer="582" to-port="2" />
-		<edge from-layer="578" from-port="0" to-layer="580" to-port="1" />
-		<edge from-layer="579" from-port="0" to-layer="580" to-port="2" />
-		<edge from-layer="580" from-port="3" to-layer="581" to-port="0" />
-		<edge from-layer="581" from-port="2" to-layer="582" to-port="3" />
-		<edge from-layer="582" from-port="4" to-layer="583" to-port="0" />
-		<edge from-layer="583" from-port="1" to-layer="596" to-port="0" />
-		<edge from-layer="583" from-port="1" to-layer="587" to-port="0" />
-		<edge from-layer="584" from-port="0" to-layer="587" to-port="1" />
-		<edge from-layer="585" from-port="0" to-layer="586" to-port="0" />
-		<edge from-layer="586" from-port="1" to-layer="587" to-port="2" />
-		<edge from-layer="587" from-port="3" to-layer="588" to-port="0" />
-		<edge from-layer="588" from-port="1" to-layer="591" to-port="0" />
-		<edge from-layer="589" from-port="0" to-layer="590" to-port="0" />
-		<edge from-layer="590" from-port="1" to-layer="591" to-port="1" />
-		<edge from-layer="591" from-port="2" to-layer="592" to-port="0" />
-		<edge from-layer="592" from-port="1" to-layer="598" to-port="0" />
-		<edge from-layer="593" from-port="0" to-layer="596" to-port="1" />
-		<edge from-layer="594" from-port="0" to-layer="595" to-port="0" />
-		<edge from-layer="595" from-port="1" to-layer="596" to-port="2" />
-		<edge from-layer="596" from-port="3" to-layer="597" to-port="0" />
-		<edge from-layer="597" from-port="1" to-layer="598" to-port="1" />
-		<edge from-layer="598" from-port="2" to-layer="599" to-port="1" />
-		<edge from-layer="599" from-port="2" to-layer="600" to-port="1" />
-		<edge from-layer="600" from-port="2" to-layer="601" to-port="0" />
+		<edge from-layer="462" from-port="2" to-layer="463" to-port="0" />
+		<edge from-layer="463" from-port="1" to-layer="464" to-port="1" />
+		<edge from-layer="464" from-port="2" to-layer="466" to-port="0" />
+		<edge from-layer="465" from-port="0" to-layer="466" to-port="1" />
+		<edge from-layer="466" from-port="2" to-layer="475" to-port="0" />
+		<edge from-layer="467" from-port="0" to-layer="468" to-port="0" />
+		<edge from-layer="468" from-port="1" to-layer="471" to-port="0" />
+		<edge from-layer="469" from-port="0" to-layer="470" to-port="0" />
+		<edge from-layer="470" from-port="1" to-layer="471" to-port="1" />
+		<edge from-layer="471" from-port="2" to-layer="473" to-port="0" />
+		<edge from-layer="472" from-port="0" to-layer="473" to-port="1" />
+		<edge from-layer="473" from-port="2" to-layer="474" to-port="0" />
+		<edge from-layer="474" from-port="1" to-layer="475" to-port="1" />
+		<edge from-layer="475" from-port="2" to-layer="477" to-port="0" />
+		<edge from-layer="476" from-port="0" to-layer="477" to-port="1" />
+		<edge from-layer="477" from-port="2" to-layer="478" to-port="0" />
 	</edges>
 	<rt_info>
-		<Runtime_version value="2024.2.0-15229-1b5a6c49e9b" />
+		<Runtime_version value="2024.6.0-17404-4c0f47d2335-releases/2024/6" />
 		<conversion_parameters>
 			<framework value="pytorch" />
 			<is_python_object value="True" />
 		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_asym" />
+				<ratio value="1" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
 		<optimum>
-			<diffusers_version value="1.19.1" />
-			<optimum_intel_version value="1.17.0.dev0+e1b6a59" />
-			<optimum_version value="1.19.1" />
-			<pytorch_version value="2.3.0+cpu" />
-			<transformers_version value="4.40.1" />
+			<diffusers_version value="0.31.0" />
+			<optimum_intel_version value="1.22.0.dev0+420fa87d" />
+			<optimum_version value="1.23.0" />
+			<pytorch_version value="2.5.1+cpu" />
+			<transformers_version value="4.46.3" />
 		</optimum>
+		<runtime_options>
+			<ACTIVATIONS_SCALE_FACTOR value="8.0" />
+		</runtime_options>
 	</rt_info>
 </net>