| <?xml version="1.0"?>
|
| <net name="Model6" version="11">
|
| <layers>
|
| <layer id="0" name="audio_input" type="Parameter" version="opset1">
|
| <data shape="?,?,80" element_type="f32" />
|
| <output>
|
| <port id="0" precision="FP32" names="audio_input">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>80</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="1" name="11" type="Const" version="opset1">
|
| <data element_type="i64" shape="" offset="0" size="8" />
|
| <output>
|
| <port id="0" precision="I64" names="11" />
|
| </output>
|
| </layer>
|
| <layer id="2" name="__module.embed/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>80</dim>
|
| </port>
|
| <port id="1" precision="I64" />
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="14,input.1">
|
| <dim>-1</dim>
|
| <dim>1</dim>
|
| <dim>-1</dim>
|
| <dim>80</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="3" name="self.embed.conv.0.weight" type="Const" version="opset1">
|
| <data element_type="i8" shape="1024, 1, 3, 3" offset="8" size="9216" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="4" name="Convert_2965993" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="5" name="self.embed.conv.0.weight/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1024, 1, 1, 1" offset="9224" size="2048" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="6" name="self.embed.conv.0.weight/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="7" name="self.embed.conv.0.weight/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="8" name="__module.embed.conv.0/aten::_convolution/Convolution" type="Convolution" version="opset1">
|
| <data strides="2, 2" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1</dim>
|
| <dim>-1</dim>
|
| <dim>80</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>40</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="9" name="__module.embed.conv.0/aten::_convolution/Reshape" type="Const" version="opset1">
|
| <data element_type="f32" shape="1, 1024, 1, 1" offset="11272" size="4096" />
|
| <output>
|
| <port id="0" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="10" name="__module.embed.conv.0/aten::_convolution/Add" type="Add" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>40</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="26,input.3">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>40</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="11" name="__module.embed.conv.1/aten::relu/Relu" type="ReLU" version="opset1">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>40</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32" names="27,input.5">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>40</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="12" name="__module.embed.conv.2/aten::_convolution/Reshape" type="Const" version="opset1">
|
| <data element_type="i8" shape="1024, 1, 1, 3, 3" offset="15368" size="9216" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="13" name="Convert_2966000" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="14" name="__module.embed.conv.2/aten::_convolution/Reshape/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1024, 1, 1, 1, 1" offset="24584" size="2048" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="15" name="__module.embed.conv.2/aten::_convolution/Reshape/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="16" name="__module.embed.conv.2/aten::_convolution/Reshape/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="17" name="__module.embed.conv.2/aten::_convolution/GroupConvolution" type="GroupConvolution" version="opset1">
|
| <data strides="2, 2" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>40</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="18" name="__module.embed.conv.2/aten::_convolution/Reshape_1" type="Const" version="opset1">
|
| <data element_type="f32" shape="1, 1024, 1, 1" offset="26632" size="4096" />
|
| <output>
|
| <port id="0" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="19" name="__module.embed.conv.2/aten::_convolution/Add" type="Add" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="34,input.7">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="20" name="self.embed.conv.3.weight" type="Const" version="opset1">
|
| <data element_type="i8" shape="1024, 1024, 1, 1" offset="30728" size="1048576" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="21" name="Convert_2961244" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="22" name="self.embed.conv.3.weight/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1024, 1, 1, 1" offset="1079304" size="2048" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="23" name="self.embed.conv.3.weight/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="24" name="self.embed.conv.3.weight/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="25" name="__module.embed.conv.3/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>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="26" name="__module.embed.conv.3/aten::_convolution/Reshape" type="Const" version="opset1">
|
| <data element_type="f32" shape="1, 1024, 1, 1" offset="1081352" size="4096" />
|
| <output>
|
| <port id="0" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="27" name="__module.embed.conv.3/aten::_convolution/Add" type="Add" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="41,input.9">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="28" name="__module.embed.conv.1/aten::relu/Relu_1" type="ReLU" version="opset1">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32" names="42,input.11">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="29" name="__module.embed.conv.5/aten::_convolution/Reshape" type="Const" version="opset1">
|
| <data element_type="i8" shape="1024, 1, 1, 3, 3" offset="1085448" size="9216" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="30" name="Convert_2966007" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="31" name="__module.embed.conv.5/aten::_convolution/Reshape/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1024, 1, 1, 1, 1" offset="1094664" size="2048" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="32" name="__module.embed.conv.5/aten::_convolution/Reshape/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="33" name="__module.embed.conv.5/aten::_convolution/Reshape/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="34" name="__module.embed.conv.5/aten::_convolution/GroupConvolution" type="GroupConvolution" version="opset1">
|
| <data strides="2, 2" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>20</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>3</dim>
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="35" name="__module.embed.conv.5/aten::_convolution/Reshape_1" type="Const" version="opset1">
|
| <data element_type="f32" shape="1, 1024, 1, 1" offset="1096712" size="4096" />
|
| <output>
|
| <port id="0" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="36" name="__module.embed.conv.5/aten::_convolution/Add" type="Add" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="49,input.13">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="37" name="self.embed.conv.6.weight" type="Const" version="opset1">
|
| <data element_type="i8" shape="1024, 1024, 1, 1" offset="1100808" size="1048576" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="38" name="Convert_2965986" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="39" name="self.embed.conv.6.weight/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1024, 1, 1, 1" offset="2149384" size="2048" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="40" name="self.embed.conv.6.weight/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="41" name="self.embed.conv.6.weight/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="42" name="__module.embed.conv.6/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>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="43" name="__module.embed.conv.6/aten::_convolution/Reshape" type="Const" version="opset1">
|
| <data element_type="f32" shape="1, 1024, 1, 1" offset="2151432" size="4096" />
|
| <output>
|
| <port id="0" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="44" name="__module.embed.conv.6/aten::_convolution/Add" type="Add" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="56,input">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="45" name="__module.embed.conv.1/aten::relu/Relu_2" type="ReLU" version="opset1">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32" names="57,x">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="46" name="__module.embed/aten::transpose/Constant" type="Const" version="opset1">
|
| <data element_type="i32" shape="4" offset="2155528" size="16" />
|
| <output>
|
| <port id="0" precision="I32">
|
| <dim>4</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="47" name="__module.embed/aten::transpose/Transpose" type="Transpose" version="opset1">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>-1</dim>
|
| <dim>10</dim>
|
| </port>
|
| <port id="1" precision="I32">
|
| <dim>4</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="60">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>10</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="48" name="Constant_97793" type="Const" version="opset1">
|
| <data element_type="i64" shape="3" offset="2155544" size="24" />
|
| <output>
|
| <port id="0" precision="I64">
|
| <dim>3</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="49" name="__module.embed/aten::reshape/Reshape" type="Reshape" version="opset1">
|
| <data special_zero="true" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| <dim>10</dim>
|
| </port>
|
| <port id="1" precision="I64">
|
| <dim>3</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="62">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="50" name="self.embed.out.weight" type="Const" version="opset1">
|
| <data element_type="i8" shape="1024, 10240" offset="2155568" size="10485760" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="51" name="Convert_2956502" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="52" name="self.embed.out.weight/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1024, 1" offset="12641328" size="2048" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="53" name="self.embed.out.weight/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="54" name="self.embed.out.weight/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="55" name="__module.embed.out/ov_ext::linear/MatMul" type="MatMul" version="opset1">
|
| <data transpose_a="false" transpose_b="true" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>10240</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1024</dim>
|
| <dim>10240</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="56" name="Constant_97783" type="Const" version="opset1">
|
| <data element_type="f32" shape="1, 1, 1024" offset="12643376" size="4096" />
|
| <output>
|
| <port id="0" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="57" name="__module.embed.out/ov_ext::linear/Add" type="Add" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1024</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="last_hidden_state">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="58" name="Result_95416" type="Result" version="opset1" output_names="last_hidden_state">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| <dim>1024</dim>
|
| </port>
|
| </input>
|
| </layer>
|
| </layers>
|
| <edges>
|
| <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
|
| <edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
|
| <edge from-layer="2" from-port="2" to-layer="8" 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="6" to-port="0" />
|
| <edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
|
| <edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
|
| <edge from-layer="7" from-port="1" 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="11" to-port="0" />
|
| <edge from-layer="11" from-port="1" to-layer="17" to-port="0" />
|
| <edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
|
| <edge from-layer="13" from-port="1" to-layer="15" to-port="0" />
|
| <edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
|
| <edge from-layer="15" from-port="2" to-layer="16" to-port="0" />
|
| <edge from-layer="16" from-port="1" to-layer="17" to-port="1" />
|
| <edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
|
| <edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
|
| <edge from-layer="19" from-port="2" to-layer="25" 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="23" to-port="0" />
|
| <edge from-layer="22" from-port="0" to-layer="23" to-port="1" />
|
| <edge from-layer="23" from-port="2" to-layer="24" to-port="0" />
|
| <edge from-layer="24" from-port="1" to-layer="25" to-port="1" />
|
| <edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
|
| <edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
|
| <edge from-layer="27" from-port="2" to-layer="28" to-port="0" />
|
| <edge from-layer="28" from-port="1" to-layer="34" to-port="0" />
|
| <edge from-layer="29" from-port="0" to-layer="30" to-port="0" />
|
| <edge from-layer="30" from-port="1" to-layer="32" to-port="0" />
|
| <edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
|
| <edge from-layer="32" from-port="2" to-layer="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="36" to-port="0" />
|
| <edge from-layer="35" from-port="0" to-layer="36" to-port="1" />
|
| <edge from-layer="36" from-port="2" to-layer="42" to-port="0" />
|
| <edge from-layer="37" from-port="0" to-layer="38" to-port="0" />
|
| <edge from-layer="38" from-port="1" to-layer="40" to-port="0" />
|
| <edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
|
| <edge from-layer="40" from-port="2" to-layer="41" to-port="0" />
|
| <edge from-layer="41" from-port="1" to-layer="42" to-port="1" />
|
| <edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
|
| <edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
|
| <edge from-layer="44" from-port="2" to-layer="45" to-port="0" />
|
| <edge from-layer="45" from-port="1" 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="55" to-port="0" />
|
| <edge from-layer="50" from-port="0" to-layer="51" to-port="0" />
|
| <edge from-layer="51" from-port="1" 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="58" to-port="0" />
|
| </edges>
|
| <rt_info>
|
| <Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
|
| <conversion_parameters>
|
| <framework value="pytorch" />
|
| <is_python_object value="True" />
|
| </conversion_parameters>
|
| <nncf>
|
| <friendly_names_were_updated value="True" />
|
| <version value="2.19.0" />
|
| <weight_compression>
|
| <advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
|
| <all_layers value="False" />
|
| <awq value="False" />
|
| <backup_mode value="int8_asym" />
|
| <compression_format value="dequantize" />
|
| <gptq value="False" />
|
| <group_size value="-1" />
|
| <ignored_scope value="[]" />
|
| <lora_correction value="False" />
|
| <mode value="int8_sym" />
|
| <ratio value="1.0" />
|
| <scale_estimation value="False" />
|
| <sensitivity_metric value="weight_quantization_error" />
|
| </weight_compression>
|
| </nncf>
|
| <optimum>
|
| <nncf_version value="2.19.0" />
|
| <optimum_intel_version value="1.27.0.dev0+132f70d" />
|
| <optimum_version value="2.1.0.dev0" />
|
| <pytorch_version value="2.9.1+cpu" />
|
| <transformers_version value="4.51.0" />
|
| </optimum>
|
| </rt_info>
|
| </net>
|
|
|
