distil-large-v2-int8-ov / openvino_decoder_model.xml
openvino-ci's picture
Upload folder using huggingface_hub
008f771 verified
<?xml version="1.0"?>
<net name="Model3" version="11">
<layers>
<layer id="1" name="decoder_input_ids" type="Parameter" version="opset1">
<data shape="?,?" element_type="i64" />
<output>
<port id="0" precision="I64" names="input_ids">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="0" name="Parameter_25934" type="Parameter" version="opset1">
<data shape="?,?,?" element_type="f32" />
<output>
<port id="0" precision="FP32" names="encoder_hidden_states">
<dim>-1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="2" name="self.model.model.decoder.embed_tokens.weight" type="Const" version="opset1">
<data element_type="u8" shape="51865, 1280" offset="0" size="66387200" />
<output>
<port id="0" precision="U8">
<dim>51865</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="3" name="Convert_42277" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>51865</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>51865</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="4" name="self.model.model.decoder.embed_tokens.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="51865, 1" offset="66387200" size="51865" />
<output>
<port id="0" precision="U8">
<dim>51865</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="5" name="Convert_42280" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>51865</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>51865</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="6" name="self.model.model.decoder.embed_tokens.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>51865</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>51865</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>51865</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="7" name="self.model.model.decoder.embed_tokens.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="51865, 1" offset="66439065" size="103730" />
<output>
<port id="0" precision="FP16">
<dim>51865</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="8" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>51865</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>51865</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>51865</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="9" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>51865</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>51865</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="10" name="Constant_31368" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="66542795" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="11" name="__module.model.model.decoder/aten::view/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="I64" names="46">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="12" name="__module.model.model.decoder.embed_tokens/aten::embedding/Convert" type="Convert" version="opset1">
<data destination_type="i32" />
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="13" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66542811" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="14" name="__module.model.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="FP32">
<dim>51865</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="FP32" names="48,inputs_embeds">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="15" name="self.model.model.decoder.embed_positions.weight" type="Const" version="opset1">
<data element_type="u8" shape="448, 1280" offset="66542815" size="573440" />
<output>
<port id="0" precision="U8">
<dim>448</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="16" name="Convert_42508" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>448</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>448</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="17" name="self.model.model.decoder.embed_positions.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="448, 1" offset="67116255" size="448" />
<output>
<port id="0" precision="U8">
<dim>448</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="18" name="Convert_42511" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>448</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>448</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="19" name="self.model.model.decoder.embed_positions.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>448</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>448</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>448</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="20" name="self.model.model.decoder.embed_positions.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="448, 1" offset="67116703" size="896" />
<output>
<port id="0" precision="FP16">
<dim>448</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="21" name="self.model.model.decoder.embed_positions.weight/fq_weights_0" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>448</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>448</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>448</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="22" name="self.model.model.decoder.embed_positions.weight/fq_weights_0/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>448</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>448</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="23" name="23" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117599" size="8" />
<output>
<port id="0" precision="I64" names="23" />
</output>
</layer>
<layer id="24" name="ShapeOf_31341" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="25" name="Constant_31342" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117607" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="26" name="Constant_31343" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117599" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="27" name="Gather_31344" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>2</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" names="43,49,59,61" />
</output>
</layer>
<layer id="28" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
<data element_type="i32" shape="" offset="67117615" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="29" name="__module.model.model.decoder/aten::arange/Range" type="Range" version="opset4">
<data output_type="f32" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="FP32" names="51,cache_position">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="30" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
</port>
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="FP32" names="52,position_ids">
<dim>1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="31" name="__module.model.model.decoder.embed_positions/aten::index/Convert" type="Convert" version="opset1">
<data destination_type="i32" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="32" name="Constant_25931" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66542811" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="33" name="__module.model.model.decoder.embed_positions/aten::index/Gather" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="FP32">
<dim>448</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
<dim>-1</dim>
</port>
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="FP32" names="55,56,positions,positions.1">
<dim>1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="34" name="__module.model.model.decoder/aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="57,input.1">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="35" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="36" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="37" name="Constant_31109" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="67117623" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="38" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="39" name="Constant_31110" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="67122743" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="40" name="__module.model.model.decoder.layers.0.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="90,hidden_states.1">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="41" name="Constant_31012" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="67127863" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="42" name="Convert_42398" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="43" name="Constant_31012/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="68766263" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="44" name="Convert_42401" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="45" name="Constant_31012/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="46" name="Constant_31012/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="68767543" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="47" name="Constant_31012/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="48" name="Constant_31012/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="49" name="Multiply_30995" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="50" name="Constant_31111" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="68770103" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="51" name="__module.model.model.decoder.layers.0.self_attn/aten::mul/Multiply" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="100,tensor.1">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="52" name="Constant_31369" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="53" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="102">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="54" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="55" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="103">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="56" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="68775271" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="57" name="Convert_42387" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="58" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="70413671" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="59" name="Convert_42390" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="60" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="61" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="70414951" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="62" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="63" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="64" name="__module.model.model.decoder.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="106,tensor.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="65" name="Constant_31370" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="66" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="108">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="67" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="68" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="109">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="69" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="119,attn_weights.1">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="70" name="__module.model.model.decoder/aten::triu/Constant" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66542811" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="71" name="__module.model.model.decoder/aten::full/Convert" type="Const" version="opset1">
<data element_type="f32" shape="" offset="70417511" size="4" />
<output>
<port id="0" precision="FP32" />
</output>
</layer>
<layer id="72" name="Constant_31351" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117607" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="73" name="Reshape_31352" 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="74" name="__module.model.model.decoder/aten::add/Multiply_3" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117607" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="75" name="__module.model.model.decoder/aten::add/Add_3" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="I64" names="62,64" />
</output>
</layer>
<layer id="76" name="Constant_23811" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66542811" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="77" name="Unsqueeze_23812" 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="78" name="__module.model.model.decoder/prim::ListConstruct_1" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="79" name="__module.model.model.decoder/aten::full/Broadcast" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="67">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="80" name="ShapeOf_31353" type="ShapeOf" version="opset3">
<data output_type="i32" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="81" name="Constant_31354" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117607" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="82" name="Constant_31355" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117599" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="83" name="Gather_31356" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I32">
<dim>2</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I32" />
</output>
</layer>
<layer id="84" name="__module.model.model.decoder/aten::triu/Constant_2" type="Const" version="opset1">
<data element_type="i32" shape="" offset="67117615" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="85" name="__module.model.model.decoder/aten::triu/Range" type="Range" version="opset4">
<data output_type="i32" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I32" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="86" name="__module.model.model.decoder/aten::triu/Unsqueeze" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32" />
</input>
<output>
<port id="2" precision="I32">
<dim>1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="87" name="__module.model.model.decoder/aten::triu/Convert" type="Const" version="opset1">
<data element_type="i32" shape="" offset="67117615" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="88" name="Convert_31359" type="Convert" version="opset1">
<data destination_type="i32" />
<input>
<port id="0" precision="I64" />
</input>
<output>
<port id="1" precision="I32" />
</output>
</layer>
<layer id="89" name="__module.model.model.decoder/aten::triu/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I32" />
</input>
<output>
<port id="2" precision="I32" />
</output>
</layer>
<layer id="90" name="__module.model.model.decoder/aten::triu/Range_1" type="Range" version="opset4">
<data output_type="i32" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I32" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="91" name="__module.model.model.decoder/aten::triu/Unsqueeze_1" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32" />
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="92" name="__module.model.model.decoder/aten::triu/GreaterEqual" type="GreaterEqual" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I32">
<dim>1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="BOOL">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="93" name="__module.model.model.decoder/aten::triu/ConvertLike" type="Const" version="opset1">
<data element_type="f32" shape="" offset="66542811" size="4" />
<output>
<port id="0" precision="FP32" />
</output>
</layer>
<layer id="94" name="__module.model.model.decoder/aten::triu/Select" type="Select" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="BOOL">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="2" precision="FP32" />
</input>
<output>
<port id="3" precision="FP32" names="68_1">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="95" name="__module.model.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66542811" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="96" name="__module.model.model.decoder/aten::arange/Constant_2" type="Const" version="opset1">
<data element_type="i32" shape="" offset="67117615" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="97" name="__module.model.model.decoder/aten::arange/Range_1" type="Range" version="opset4">
<data output_type="f32" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="FP32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="98" name="__module.model.model.decoder/aten::arange/ConvertLike" type="Convert" version="opset1">
<data destination_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64" names="69">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="99" name="__module.model.model.decoder/aten::gt/Convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="I64">
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="100" name="Constant_23914" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="70417515" size="16" />
<output>
<port id="0" precision="I64" names="70">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="101" name="__module.model.model.decoder/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="71">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="102" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="BOOL" names="72">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="103" name="__module.model.model.decoder/aten::mul_/ConvertLike" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="BOOL">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="104" name="__module.model.model.decoder/aten::mul_/Multiply" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="68,causal_mask.1">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="105" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_1" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="FP32" names="74">
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="106" name="28" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117607" size="8" />
<output>
<port id="0" precision="I64" names="28" />
</output>
</layer>
<layer id="107" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze_2" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="FP32" names="75,76,77">
<dim>1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="108" name="Constant_31348" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117599" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="109" name="Constant_31349" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117599" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="110" name="Gather_31350" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>2</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" names="145,210,260,65,95">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="111" name="Constant_30340" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117607" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="112" name="Constant_30342" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117607" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="113" name="Constant_30344" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117607" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="114" name="__module.model.model.decoder/prim::ListConstruct_2" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>1</dim>
</port>
<port id="3" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="4" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="115" name="__module.model.model.decoder/aten::expand/Broadcast" type="Broadcast" version="opset3">
<data mode="bidirectional" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="121,122,123,236,237,238,79,attention_mask">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="116" name="Constant_24348" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117599" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="117" name="ShapeOf_31364" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="118" name="Constant_31365" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117607" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="119" name="Constant_31366" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67117599" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="120" name="Gather_31367" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" names="120,235">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="121" name="Constant_24351" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67117607" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="122" name="__module.model.model.decoder/aten::slice/Reshape_1" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70417531" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="123" name="__module.model.model.decoder.layers.0.self_attn/aten::slice/Slice_3" type="Slice" version="opset8">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>1</dim>
</port>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="5" precision="FP32" names="124,239,causal_mask,causal_mask.5">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="124" name="__module.model.model.decoder.layers.0.self_attn/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="125,input.3">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="125" name="__module.model.model.decoder.layers.0.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
<data axis="-1" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="126,input.5">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="126" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="70417539" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="127" name="Convert_42376" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="128" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="72055939" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="129" name="Convert_42379" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="130" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="131" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="72057219" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="132" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="133" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="134" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="135" name="Constant_31112" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="72059779" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="136" name="__module.model.model.decoder.layers.0.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="113,tensor.5">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="137" name="Constant_31371" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="138" name="__module.model.model.decoder.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="115">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="139" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="140" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="116">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="141" name="__module.model.model.decoder.layers.0.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="128,attn_output.1">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="142" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="143" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="129,attn_output.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="144" name="Constant_31372" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="72064899" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="145" name="__module.model.model.decoder.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="131">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="146" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="72064923" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="147" name="Convert_42409" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="148" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="73703323" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="149" name="Convert_42412" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="150" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="151" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="73704603" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="152" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="153" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="154" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="155" name="Constant_31113" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="73707163" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="156" name="__module.model.model.decoder.layers.0.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="134,input.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="157" name="__module.model.model.decoder.layers.0/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="136,residual.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="158" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="159" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="160" name="Constant_31114" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="73712283" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="161" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="162" name="Constant_31115" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="73717403" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="163" name="__module.model.model.decoder.layers.0.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="140,hidden_states.5">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="164" name="Constant_31015" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="73722523" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="165" name="Convert_42420" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="166" name="Constant_31015/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="75360923" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="167" name="Convert_42423" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="168" name="Constant_31015/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="169" name="Constant_31015/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="75362203" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="170" name="Constant_31015/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="171" name="Constant_31015/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="172" name="Multiply_30999" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="173" name="Constant_31116" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="75364763" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="174" name="__module.model.model.decoder.layers.0.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="150,tensor.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="175" name="Constant_31373" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="176" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="152">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="177" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="178" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="153">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="179" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="75369883" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="180" name="Convert_42365" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="181" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="77008283" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="182" name="Convert_42368" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="183" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="184" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="77009563" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="185" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="186" name="self.model.model.decoder.layers.0.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="187" name="__module.model.model.decoder.layers.0.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="156,tensor.9">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="188" name="Constant_24572" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="77012123" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="189" name="Constant_24573" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="77012131" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="190" name="Constant_24574" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="77012139" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="191" name="__module.model.model.decoder.layers.0.encoder_attn/prim::ListConstruct_1" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>1</dim>
</port>
<port id="3" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="4" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="192" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="158">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="193" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="194" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="159">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="195" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="169,input.9">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="196" name="__module.model.model.decoder.layers.0.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
<data axis="-1" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="170,input.11">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="197" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="77012147" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="198" name="Convert_42354" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="199" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="78650547" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="200" name="Convert_42357" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="201" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="202" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="78651827" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="203" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="204" name="self.model.model.decoder.layers.0.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="205" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="206" name="Constant_31117" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="78654387" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="207" name="__module.model.model.decoder.layers.0.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="163,tensor.11">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="208" name="__module.model.model.decoder.layers.0.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="165">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="209" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="210" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="166">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="211" name="__module.model.model.decoder.layers.0.encoder_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="172,attn_output.5">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="212" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="213" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="173,attn_output.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="214" name="Constant_31374" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="78659507" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="215" name="__module.model.model.decoder.layers.0.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="175">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="216" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="78659531" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="217" name="Convert_42431" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="218" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="80297931" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="219" name="Convert_42434" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="220" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="221" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="80299211" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="222" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="223" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="224" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="225" name="Constant_31118" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="80301771" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="226" name="__module.model.model.decoder.layers.0.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="178,input.13">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="227" name="__module.model.model.decoder.layers.0/aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="180,residual.5">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="228" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="229" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="230" name="Constant_31119" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="80306891" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="231" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="232" name="Constant_31120" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="80312011" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="233" name="__module.model.model.decoder.layers.0.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="184">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="234" name="self.model.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1280" offset="80317131" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="235" name="Convert_42288" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="236" name="self.model.model.decoder.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1" offset="86870731" size="5120" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="237" name="Convert_42291" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="238" name="self.model.model.decoder.layers.0.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="239" name="self.model.model.decoder.layers.0.fc1.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="5120, 1" offset="86875851" size="10240" />
<output>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="240" name="self.model.model.decoder.layers.0.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="241" name="self.model.model.decoder.layers.0.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="242" name="__module.model.model.decoder.layers.0.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>5120</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="243" name="Constant_31121" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 5120" offset="86886091" size="20480" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="244" name="__module.model.model.decoder.layers.0.fc1/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="187">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="245" name="__module.model.model.decoder.layers.0.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
<data approximation_mode="ERF" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="188,input.15">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="246" name="self.model.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 5120" offset="86906571" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="247" name="Convert_42299" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="248" name="self.model.model.decoder.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="93460171" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="249" name="Convert_42302" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="250" name="self.model.model.decoder.layers.0.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="251" name="self.model.model.decoder.layers.0.fc2.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="93461451" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="252" name="self.model.model.decoder.layers.0.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="253" name="self.model.model.decoder.layers.0.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="254" name="__module.model.model.decoder.layers.0.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="255" name="Constant_31122" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="93464011" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="256" name="__module.model.model.decoder.layers.0.fc2/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="192,input.17">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="257" name="__module.model.model.decoder.layers.0/aten::add/Add_2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="194,residual.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="258" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="259" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="260" name="Constant_31123" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="93469131" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="261" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="262" name="Constant_31124" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="93474251" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="263" name="__module.model.model.decoder.layers.1.self_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="205,hidden_states.11">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="264" name="Constant_31018" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="93479371" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="265" name="Convert_42464" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="266" name="Constant_31018/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="95117771" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="267" name="Convert_42467" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="268" name="Constant_31018/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="269" name="Constant_31018/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="95119051" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="270" name="Constant_31018/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="271" name="Constant_31018/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="272" name="Multiply_31003" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="273" name="Constant_31125" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="95121611" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="274" name="__module.model.model.decoder.layers.1.self_attn/aten::mul/Multiply" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="215,tensor.13">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="275" name="Constant_31375" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="276" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="217">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="277" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="278" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="218">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="279" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="95126731" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="280" name="Convert_42453" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="281" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="96765131" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="282" name="Convert_42456" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="283" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="284" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="96766411" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="285" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="286" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="287" name="__module.model.model.decoder.layers.1.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="221,tensor.15">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="288" name="Constant_31376" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="289" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="223">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="290" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="291" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="224">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="292" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="234,attn_weights">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="293" name="__module.model.model.decoder.layers.1.self_attn/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="240,input.19">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="294" name="__module.model.model.decoder.layers.1.self_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
<data axis="-1" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="241,input.21">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="295" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="96768971" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="296" name="Convert_42442" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="297" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="98407371" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="298" name="Convert_42445" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="299" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="300" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="98408651" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="301" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="302" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="303" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="304" name="Constant_31126" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="98411211" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="305" name="__module.model.model.decoder.layers.1.self_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="228,tensor.17">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="306" name="Constant_31377" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="307" name="__module.model.model.decoder.layers.1.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="230">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="308" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="309" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="231">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="310" name="__module.model.model.decoder.layers.1.self_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="243,attn_output.9">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="311" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="312" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="244,attn_output.11">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="313" name="Constant_31378" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="72064899" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="314" name="__module.model.model.decoder.layers.1.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="246">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="315" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="98416331" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="316" name="Convert_42475" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="317" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="100054731" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="318" name="Convert_42478" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="319" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="320" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="100056011" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="321" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="322" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="323" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="324" name="Constant_31127" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="100058571" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="325" name="__module.model.model.decoder.layers.1.self_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="249,input.23">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="326" name="__module.model.model.decoder.layers.1/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="251,residual.9">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="327" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="328" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="329" name="Constant_31128" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="100063691" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="330" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="331" name="Constant_31129" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="100068811" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="332" name="__module.model.model.decoder.layers.1.encoder_attn_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="255,hidden_states.15">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="333" name="Constant_31021" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="100073931" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="334" name="Convert_42486" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="335" name="Constant_31021/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="101712331" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="336" name="Convert_42489" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="337" name="Constant_31021/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="338" name="Constant_31021/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="101713611" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="339" name="Constant_31021/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="340" name="Constant_31021/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="341" name="Multiply_31007" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="342" name="Constant_31130" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="101716171" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="343" name="__module.model.model.decoder.layers.1.encoder_attn/aten::mul/Multiply" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="265,tensor.19">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="344" name="Constant_31379" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68775223" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="345" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="267">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="346" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="347" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="268">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="348" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="101721291" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="349" name="Convert_42343" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="350" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="103359691" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="351" name="Convert_42346" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="352" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="353" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="103360971" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="354" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="355" name="self.model.model.decoder.layers.1.encoder_attn.k_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="356" name="__module.model.model.decoder.layers.1.encoder_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="271,tensor.21">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="357" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="273">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="358" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="359" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="274">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="360" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="284,input.25">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="361" name="__module.model.model.decoder.layers.1.encoder_attn/aten::softmax/Softmax" type="SoftMax" version="opset8">
<data axis="-1" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="285,input.27">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="362" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="103363531" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="363" name="Convert_42332" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="364" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="105001931" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="365" name="Convert_42335" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="366" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="367" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="105003211" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="368" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="369" name="self.model.model.decoder.layers.1.encoder_attn.v_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="370" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="371" name="Constant_31131" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="105005771" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="372" name="__module.model.model.decoder.layers.1.encoder_attn.v_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="278,tensor">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="373" name="__module.model.model.decoder.layers.1.encoder_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="280">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="374" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_3" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="375" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="281">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="376" name="__module.model.model.decoder.layers.1.encoder_attn/aten::matmul/MatMul_1" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="287,attn_output.13">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="377" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_4" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68775255" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="378" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_4" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="288,attn_output">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="379" name="Constant_31380" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="78659507" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="380" name="__module.model.model.decoder.layers.1.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="290">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="381" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="105010891" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="382" name="Convert_42497" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="383" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="106649291" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="384" name="Convert_42500" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="385" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="386" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="106650571" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="387" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="388" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="389" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="390" name="Constant_31132" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="106653131" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="391" name="__module.model.model.decoder.layers.1.encoder_attn.out_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="293,input.29">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="392" name="__module.model.model.decoder.layers.1/aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="295,residual">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="393" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="394" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="395" name="Constant_31133" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="106658251" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="396" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="397" name="Constant_31134" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="106663371" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="398" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="299">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="399" name="self.model.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1280" offset="106668491" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="400" name="Convert_42310" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="401" name="self.model.model.decoder.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1" offset="113222091" size="5120" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="402" name="Convert_42313" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="403" name="self.model.model.decoder.layers.1.fc1.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="404" name="self.model.model.decoder.layers.1.fc1.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="5120, 1" offset="113227211" size="10240" />
<output>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="405" name="self.model.model.decoder.layers.1.fc1.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="406" name="self.model.model.decoder.layers.1.fc1.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="407" name="__module.model.model.decoder.layers.1.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>5120</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="408" name="Constant_31135" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 5120" offset="113237451" size="20480" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="409" name="__module.model.model.decoder.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="302">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="410" name="__module.model.model.decoder.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
<data approximation_mode="ERF" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="303,input.31">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="411" name="self.model.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 5120" offset="113257931" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="412" name="Convert_42321" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="413" name="self.model.model.decoder.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="119811531" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="414" name="Convert_42324" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="415" name="self.model.model.decoder.layers.1.fc2.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="416" name="self.model.model.decoder.layers.1.fc2.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="119812811" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="417" name="self.model.model.decoder.layers.1.fc2.weight/fq_weights_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="418" name="self.model.model.decoder.layers.1.fc2.weight/fq_weights_1/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="419" name="__module.model.model.decoder.layers.1.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP32">
<dim>1280</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="420" name="Constant_31136" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="119815371" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="421" name="__module.model.model.decoder.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="307,input">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="422" name="__module.model.model.decoder.layers.1/aten::add/Add_2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="309">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="423" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67117619" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="424" name="__module.model.model.decoder.layer_norm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="425" name="Constant_31137" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="119820491" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="426" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="427" name="Constant_31138" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="119825611" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="428" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="313">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="429" name="__module.model.proj_out/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>51865</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="logits">
<dim>-1</dim>
<dim>-1</dim>
<dim>51865</dim>
</port>
</output>
</layer>
<layer id="430" name="Result_25933" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>51865</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="187" to-port="0" />
<edge from-layer="0" from-port="0" to-layer="205" to-port="0" />
<edge from-layer="0" from-port="0" to-layer="370" to-port="0" />
<edge from-layer="0" from-port="0" to-layer="356" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="11" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="24" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
<edge from-layer="3" from-port="1" to-layer="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="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="9" to-port="0" />
<edge from-layer="9" from-port="1" to-layer="14" to-port="0" />
<edge from-layer="9" from-port="1" to-layer="429" to-port="1" />
<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
<edge from-layer="11" from-port="2" to-layer="12" to-port="0" />
<edge from-layer="12" from-port="1" to-layer="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="34" to-port="0" />
<edge from-layer="15" from-port="0" to-layer="16" to-port="0" />
<edge from-layer="16" from-port="1" to-layer="19" to-port="0" />
<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
<edge from-layer="18" from-port="1" to-layer="19" to-port="1" />
<edge from-layer="19" from-port="2" to-layer="21" to-port="0" />
<edge from-layer="20" from-port="0" to-layer="21" to-port="1" />
<edge from-layer="21" from-port="2" to-layer="22" to-port="0" />
<edge from-layer="22" from-port="1" to-layer="33" to-port="0" />
<edge from-layer="23" from-port="0" to-layer="105" to-port="1" />
<edge from-layer="23" from-port="0" to-layer="30" to-port="1" />
<edge from-layer="23" from-port="0" to-layer="29" to-port="0" />
<edge from-layer="24" from-port="1" to-layer="110" to-port="0" />
<edge from-layer="24" from-port="1" to-layer="27" to-port="0" />
<edge from-layer="25" from-port="0" to-layer="27" to-port="1" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="2" />
<edge from-layer="27" from-port="3" to-layer="73" to-port="0" />
<edge from-layer="27" from-port="3" to-layer="75" to-port="0" />
<edge from-layer="27" from-port="3" to-layer="88" to-port="0" />
<edge from-layer="27" from-port="3" 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="29" from-port="3" to-layer="101" to-port="0" />
<edge from-layer="30" from-port="2" to-layer="31" to-port="0" />
<edge from-layer="31" from-port="1" to-layer="33" to-port="1" />
<edge from-layer="32" from-port="0" to-layer="33" to-port="2" />
<edge from-layer="33" from-port="3" to-layer="34" to-port="1" />
<edge from-layer="34" from-port="2" to-layer="36" to-port="0" />
<edge from-layer="34" from-port="2" to-layer="157" 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="38" to-port="0" />
<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
<edge from-layer="40" from-port="2" to-layer="117" to-port="0" />
<edge from-layer="40" from-port="2" to-layer="49" to-port="0" />
<edge from-layer="40" from-port="2" to-layer="64" to-port="0" />
<edge from-layer="40" from-port="2" to-layer="134" to-port="0" />
<edge from-layer="41" from-port="0" to-layer="42" to-port="0" />
<edge from-layer="42" from-port="1" to-layer="45" to-port="0" />
<edge from-layer="43" from-port="0" to-layer="44" to-port="0" />
<edge from-layer="44" from-port="1" to-layer="45" to-port="1" />
<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="48" to-port="0" />
<edge from-layer="48" from-port="1" to-layer="49" to-port="1" />
<edge from-layer="49" from-port="2" to-layer="51" to-port="0" />
<edge from-layer="50" from-port="0" to-layer="51" to-port="1" />
<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="55" to-port="0" />
<edge from-layer="54" from-port="0" to-layer="55" to-port="1" />
<edge from-layer="55" from-port="2" to-layer="69" to-port="0" />
<edge from-layer="56" from-port="0" to-layer="57" to-port="0" />
<edge from-layer="57" from-port="1" to-layer="60" to-port="0" />
<edge from-layer="58" from-port="0" to-layer="59" to-port="0" />
<edge from-layer="59" from-port="1" to-layer="60" to-port="1" />
<edge from-layer="60" from-port="2" to-layer="62" to-port="0" />
<edge from-layer="61" from-port="0" to-layer="62" to-port="1" />
<edge from-layer="62" from-port="2" 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="65" from-port="0" 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="69" to-port="1" />
<edge from-layer="69" from-port="2" to-layer="124" to-port="0" />
<edge from-layer="70" from-port="0" to-layer="86" to-port="1" />
<edge from-layer="70" from-port="0" to-layer="85" to-port="0" />
<edge from-layer="71" from-port="0" to-layer="79" to-port="0" />
<edge from-layer="72" from-port="0" to-layer="73" to-port="1" />
<edge from-layer="73" from-port="2" to-layer="78" to-port="0" />
<edge from-layer="74" from-port="0" to-layer="75" to-port="1" />
<edge from-layer="75" from-port="2" to-layer="97" to-port="1" />
<edge from-layer="75" from-port="2" to-layer="77" to-port="0" />
<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
<edge from-layer="77" from-port="2" to-layer="78" to-port="1" />
<edge from-layer="78" from-port="2" to-layer="79" to-port="1" />
<edge from-layer="79" from-port="2" to-layer="94" to-port="1" />
<edge from-layer="79" from-port="2" to-layer="80" to-port="0" />
<edge from-layer="80" from-port="1" to-layer="83" to-port="0" />
<edge from-layer="81" from-port="0" to-layer="83" to-port="1" />
<edge from-layer="82" from-port="0" to-layer="83" to-port="2" />
<edge from-layer="83" from-port="3" to-layer="85" to-port="1" />
<edge from-layer="84" from-port="0" to-layer="85" to-port="2" />
<edge from-layer="84" from-port="0" to-layer="91" to-port="1" />
<edge from-layer="84" from-port="0" to-layer="90" to-port="2" />
<edge from-layer="85" from-port="3" to-layer="86" to-port="0" />
<edge from-layer="86" from-port="2" to-layer="92" to-port="0" />
<edge from-layer="87" from-port="0" to-layer="89" to-port="1" />
<edge from-layer="87" from-port="0" to-layer="90" to-port="0" />
<edge from-layer="88" from-port="1" to-layer="89" to-port="0" />
<edge from-layer="89" from-port="2" to-layer="90" to-port="1" />
<edge from-layer="90" from-port="3" to-layer="91" to-port="0" />
<edge from-layer="91" from-port="2" to-layer="92" to-port="1" />
<edge from-layer="92" from-port="2" to-layer="94" to-port="0" />
<edge from-layer="93" from-port="0" to-layer="94" to-port="2" />
<edge from-layer="94" from-port="3" to-layer="104" to-port="0" />
<edge from-layer="95" from-port="0" to-layer="97" to-port="0" />
<edge from-layer="96" from-port="0" to-layer="97" to-port="2" />
<edge from-layer="97" from-port="3" to-layer="98" to-port="0" />
<edge from-layer="98" from-port="1" to-layer="99" to-port="0" />
<edge from-layer="99" from-port="1" to-layer="102" to-port="0" />
<edge from-layer="100" from-port="0" to-layer="101" to-port="1" />
<edge from-layer="101" from-port="2" to-layer="102" to-port="1" />
<edge from-layer="102" from-port="2" to-layer="103" to-port="0" />
<edge from-layer="103" from-port="1" to-layer="104" to-port="1" />
<edge from-layer="104" from-port="2" to-layer="105" to-port="0" />
<edge from-layer="105" from-port="2" to-layer="107" to-port="0" />
<edge from-layer="106" from-port="0" to-layer="107" to-port="1" />
<edge from-layer="107" from-port="2" to-layer="115" to-port="0" />
<edge from-layer="108" from-port="0" to-layer="110" to-port="1" />
<edge from-layer="109" from-port="0" to-layer="110" to-port="2" />
<edge from-layer="110" from-port="3" to-layer="191" to-port="0" />
<edge from-layer="110" from-port="3" to-layer="114" to-port="0" />
<edge from-layer="111" from-port="0" to-layer="114" to-port="1" />
<edge from-layer="112" from-port="0" to-layer="114" to-port="2" />
<edge from-layer="113" from-port="0" to-layer="114" to-port="3" />
<edge from-layer="114" from-port="4" to-layer="115" to-port="1" />
<edge from-layer="115" from-port="2" to-layer="123" to-port="0" />
<edge from-layer="116" from-port="0" to-layer="123" to-port="1" />
<edge from-layer="117" from-port="1" to-layer="120" to-port="0" />
<edge from-layer="118" from-port="0" to-layer="120" to-port="1" />
<edge from-layer="119" from-port="0" to-layer="120" to-port="2" />
<edge from-layer="120" from-port="3" to-layer="123" to-port="2" />
<edge from-layer="121" from-port="0" to-layer="123" to-port="3" />
<edge from-layer="122" from-port="0" to-layer="123" to-port="4" />
<edge from-layer="123" from-port="5" to-layer="124" to-port="1" />
<edge from-layer="123" from-port="5" to-layer="293" to-port="1" />
<edge from-layer="124" from-port="2" to-layer="125" to-port="0" />
<edge from-layer="125" from-port="1" to-layer="141" to-port="0" />
<edge from-layer="126" from-port="0" to-layer="127" to-port="0" />
<edge from-layer="127" from-port="1" to-layer="130" to-port="0" />
<edge from-layer="128" from-port="0" to-layer="129" to-port="0" />
<edge from-layer="129" from-port="1" to-layer="130" to-port="1" />
<edge from-layer="130" from-port="2" to-layer="132" to-port="0" />
<edge from-layer="131" from-port="0" to-layer="132" to-port="1" />
<edge from-layer="132" from-port="2" to-layer="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="136" to-port="0" />
<edge from-layer="135" from-port="0" to-layer="136" to-port="1" />
<edge from-layer="136" from-port="2" to-layer="138" to-port="0" />
<edge from-layer="137" from-port="0" to-layer="138" to-port="1" />
<edge from-layer="138" from-port="2" to-layer="140" to-port="0" />
<edge from-layer="139" from-port="0" to-layer="140" to-port="1" />
<edge from-layer="140" from-port="2" to-layer="141" to-port="1" />
<edge from-layer="141" from-port="2" to-layer="143" to-port="0" />
<edge from-layer="142" from-port="0" to-layer="143" to-port="1" />
<edge from-layer="143" from-port="2" to-layer="145" to-port="0" />
<edge from-layer="144" from-port="0" to-layer="145" to-port="1" />
<edge from-layer="145" from-port="2" to-layer="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="155" from-port="0" to-layer="156" to-port="1" />
<edge from-layer="156" from-port="2" to-layer="157" to-port="1" />
<edge from-layer="157" from-port="2" to-layer="227" to-port="0" />
<edge from-layer="157" from-port="2" to-layer="159" to-port="0" />
<edge from-layer="158" from-port="0" to-layer="159" to-port="1" />
<edge from-layer="159" from-port="2" to-layer="161" to-port="0" />
<edge from-layer="160" from-port="0" to-layer="161" to-port="1" />
<edge from-layer="161" from-port="2" to-layer="163" to-port="0" />
<edge from-layer="162" from-port="0" to-layer="163" to-port="1" />
<edge from-layer="163" from-port="2" to-layer="172" to-port="0" />
<edge from-layer="164" from-port="0" to-layer="165" to-port="0" />
<edge from-layer="165" from-port="1" to-layer="168" to-port="0" />
<edge from-layer="166" from-port="0" to-layer="167" to-port="0" />
<edge from-layer="167" from-port="1" to-layer="168" to-port="1" />
<edge from-layer="168" from-port="2" to-layer="170" to-port="0" />
<edge from-layer="169" from-port="0" to-layer="170" to-port="1" />
<edge from-layer="170" from-port="2" to-layer="171" to-port="0" />
<edge from-layer="171" from-port="1" to-layer="172" to-port="1" />
<edge from-layer="172" from-port="2" to-layer="174" to-port="0" />
<edge from-layer="173" from-port="0" to-layer="174" to-port="1" />
<edge from-layer="174" from-port="2" to-layer="176" to-port="0" />
<edge from-layer="175" from-port="0" to-layer="176" to-port="1" />
<edge from-layer="176" from-port="2" to-layer="178" to-port="0" />
<edge from-layer="177" from-port="0" to-layer="178" to-port="1" />
<edge from-layer="178" from-port="2" to-layer="195" to-port="0" />
<edge from-layer="179" from-port="0" to-layer="180" to-port="0" />
<edge from-layer="180" from-port="1" to-layer="183" 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="185" to-port="0" />
<edge from-layer="184" from-port="0" to-layer="185" to-port="1" />
<edge from-layer="185" from-port="2" to-layer="186" to-port="0" />
<edge from-layer="186" from-port="1" to-layer="187" to-port="1" />
<edge from-layer="187" from-port="2" to-layer="192" to-port="0" />
<edge from-layer="188" from-port="0" to-layer="191" to-port="1" />
<edge from-layer="189" from-port="0" to-layer="191" to-port="2" />
<edge from-layer="190" from-port="0" to-layer="191" to-port="3" />
<edge from-layer="191" from-port="4" to-layer="357" to-port="1" />
<edge from-layer="191" from-port="4" to-layer="373" to-port="1" />
<edge from-layer="191" from-port="4" to-layer="208" to-port="1" />
<edge from-layer="191" from-port="4" to-layer="192" to-port="1" />
<edge from-layer="192" from-port="2" to-layer="194" to-port="0" />
<edge from-layer="193" from-port="0" to-layer="194" to-port="1" />
<edge from-layer="194" from-port="2" to-layer="195" to-port="1" />
<edge from-layer="195" from-port="2" to-layer="196" to-port="0" />
<edge from-layer="196" from-port="1" to-layer="211" to-port="0" />
<edge from-layer="197" from-port="0" to-layer="198" to-port="0" />
<edge from-layer="198" from-port="1" to-layer="201" 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="201" to-port="1" />
<edge from-layer="201" from-port="2" to-layer="203" to-port="0" />
<edge from-layer="202" from-port="0" to-layer="203" to-port="1" />
<edge from-layer="203" from-port="2" to-layer="204" to-port="0" />
<edge from-layer="204" from-port="1" to-layer="205" to-port="1" />
<edge from-layer="205" from-port="2" to-layer="207" to-port="0" />
<edge from-layer="206" from-port="0" to-layer="207" to-port="1" />
<edge from-layer="207" from-port="2" to-layer="208" to-port="0" />
<edge from-layer="208" from-port="2" to-layer="210" to-port="0" />
<edge from-layer="209" from-port="0" to-layer="210" to-port="1" />
<edge from-layer="210" from-port="2" to-layer="211" to-port="1" />
<edge from-layer="211" from-port="2" to-layer="213" to-port="0" />
<edge from-layer="212" from-port="0" to-layer="213" to-port="1" />
<edge from-layer="213" from-port="2" to-layer="215" to-port="0" />
<edge from-layer="214" from-port="0" to-layer="215" to-port="1" />
<edge from-layer="215" from-port="2" to-layer="224" to-port="0" />
<edge from-layer="216" from-port="0" to-layer="217" to-port="0" />
<edge from-layer="217" from-port="1" to-layer="220" to-port="0" />
<edge from-layer="218" from-port="0" to-layer="219" to-port="0" />
<edge from-layer="219" from-port="1" to-layer="220" to-port="1" />
<edge from-layer="220" from-port="2" to-layer="222" to-port="0" />
<edge from-layer="221" from-port="0" to-layer="222" to-port="1" />
<edge from-layer="222" from-port="2" 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="226" to-port="0" />
<edge from-layer="225" from-port="0" to-layer="226" to-port="1" />
<edge from-layer="226" from-port="2" to-layer="227" to-port="1" />
<edge from-layer="227" from-port="2" to-layer="229" to-port="0" />
<edge from-layer="227" from-port="2" to-layer="257" 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="0" to-layer="231" to-port="1" />
<edge from-layer="231" from-port="2" to-layer="233" to-port="0" />
<edge from-layer="232" from-port="0" to-layer="233" to-port="1" />
<edge from-layer="233" from-port="2" to-layer="242" to-port="0" />
<edge from-layer="234" from-port="0" to-layer="235" to-port="0" />
<edge from-layer="235" from-port="1" to-layer="238" to-port="0" />
<edge from-layer="236" from-port="0" 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="0" />
<edge from-layer="241" from-port="1" to-layer="242" to-port="1" />
<edge from-layer="242" from-port="2" to-layer="244" to-port="0" />
<edge from-layer="243" from-port="0" to-layer="244" to-port="1" />
<edge from-layer="244" from-port="2" to-layer="245" to-port="0" />
<edge from-layer="245" from-port="1" to-layer="254" to-port="0" />
<edge from-layer="246" from-port="0" to-layer="247" to-port="0" />
<edge from-layer="247" from-port="1" to-layer="250" to-port="0" />
<edge from-layer="248" from-port="0" 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="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="253" to-port="0" />
<edge from-layer="253" from-port="1" to-layer="254" to-port="1" />
<edge from-layer="254" from-port="2" to-layer="256" to-port="0" />
<edge from-layer="255" from-port="0" to-layer="256" to-port="1" />
<edge from-layer="256" from-port="2" to-layer="257" to-port="1" />
<edge from-layer="257" from-port="2" to-layer="259" to-port="0" />
<edge from-layer="257" from-port="2" to-layer="326" to-port="0" />
<edge from-layer="258" from-port="0" to-layer="259" to-port="1" />
<edge from-layer="259" from-port="2" to-layer="261" to-port="0" />
<edge from-layer="260" from-port="0" 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="272" to-port="0" />
<edge from-layer="263" from-port="2" to-layer="287" to-port="0" />
<edge from-layer="263" from-port="2" to-layer="303" to-port="0" />
<edge from-layer="264" from-port="0" to-layer="265" to-port="0" />
<edge from-layer="265" from-port="1" to-layer="268" to-port="0" />
<edge from-layer="266" from-port="0" to-layer="267" to-port="0" />
<edge from-layer="267" from-port="1" to-layer="268" to-port="1" />
<edge from-layer="268" from-port="2" to-layer="270" to-port="0" />
<edge from-layer="269" from-port="0" to-layer="270" to-port="1" />
<edge from-layer="270" from-port="2" to-layer="271" to-port="0" />
<edge from-layer="271" from-port="1" to-layer="272" to-port="1" />
<edge from-layer="272" from-port="2" to-layer="274" to-port="0" />
<edge from-layer="273" from-port="0" to-layer="274" to-port="1" />
<edge from-layer="274" from-port="2" to-layer="276" to-port="0" />
<edge from-layer="275" from-port="0" to-layer="276" to-port="1" />
<edge from-layer="276" from-port="2" to-layer="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="292" to-port="0" />
<edge from-layer="279" from-port="0" to-layer="280" to-port="0" />
<edge from-layer="280" from-port="1" to-layer="283" to-port="0" />
<edge from-layer="281" from-port="0" to-layer="282" to-port="0" />
<edge from-layer="282" from-port="1" to-layer="283" to-port="1" />
<edge from-layer="283" from-port="2" to-layer="285" to-port="0" />
<edge from-layer="284" from-port="0" to-layer="285" to-port="1" />
<edge from-layer="285" from-port="2" to-layer="286" to-port="0" />
<edge from-layer="286" from-port="1" to-layer="287" to-port="1" />
<edge from-layer="287" from-port="2" to-layer="289" to-port="0" />
<edge from-layer="288" from-port="0" to-layer="289" to-port="1" />
<edge from-layer="289" from-port="2" to-layer="291" to-port="0" />
<edge from-layer="290" from-port="0" to-layer="291" to-port="1" />
<edge from-layer="291" from-port="2" to-layer="292" to-port="1" />
<edge from-layer="292" from-port="2" to-layer="293" to-port="0" />
<edge from-layer="293" from-port="2" to-layer="294" to-port="0" />
<edge from-layer="294" from-port="1" to-layer="310" to-port="0" />
<edge from-layer="295" from-port="0" to-layer="296" to-port="0" />
<edge from-layer="296" from-port="1" to-layer="299" to-port="0" />
<edge from-layer="297" from-port="0" to-layer="298" to-port="0" />
<edge from-layer="298" from-port="1" to-layer="299" to-port="1" />
<edge from-layer="299" from-port="2" to-layer="301" to-port="0" />
<edge from-layer="300" from-port="0" 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="303" to-port="1" />
<edge from-layer="303" from-port="2" to-layer="305" to-port="0" />
<edge from-layer="304" from-port="0" to-layer="305" to-port="1" />
<edge from-layer="305" from-port="2" to-layer="307" to-port="0" />
<edge from-layer="306" from-port="0" to-layer="307" to-port="1" />
<edge from-layer="307" from-port="2" to-layer="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="1" />
<edge from-layer="310" from-port="2" to-layer="312" to-port="0" />
<edge from-layer="311" from-port="0" to-layer="312" to-port="1" />
<edge from-layer="312" from-port="2" to-layer="314" to-port="0" />
<edge from-layer="313" from-port="0" to-layer="314" to-port="1" />
<edge from-layer="314" from-port="2" to-layer="323" to-port="0" />
<edge from-layer="315" from-port="0" to-layer="316" to-port="0" />
<edge from-layer="316" from-port="1" to-layer="319" to-port="0" />
<edge from-layer="317" from-port="0" to-layer="318" to-port="0" />
<edge from-layer="318" from-port="1" to-layer="319" to-port="1" />
<edge from-layer="319" from-port="2" to-layer="321" to-port="0" />
<edge from-layer="320" from-port="0" to-layer="321" to-port="1" />
<edge from-layer="321" from-port="2" to-layer="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="1" />
<edge from-layer="326" from-port="2" to-layer="328" to-port="0" />
<edge from-layer="326" from-port="2" to-layer="392" to-port="0" />
<edge from-layer="327" from-port="0" to-layer="328" to-port="1" />
<edge from-layer="328" from-port="2" to-layer="330" to-port="0" />
<edge from-layer="329" from-port="0" to-layer="330" to-port="1" />
<edge from-layer="330" from-port="2" to-layer="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="341" to-port="0" />
<edge from-layer="333" from-port="0" to-layer="334" to-port="0" />
<edge from-layer="334" from-port="1" 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="339" to-port="0" />
<edge from-layer="338" from-port="0" to-layer="339" to-port="1" />
<edge from-layer="339" from-port="2" to-layer="340" to-port="0" />
<edge from-layer="340" from-port="1" to-layer="341" to-port="1" />
<edge from-layer="341" from-port="2" to-layer="343" to-port="0" />
<edge from-layer="342" from-port="0" to-layer="343" to-port="1" />
<edge from-layer="343" from-port="2" to-layer="345" to-port="0" />
<edge from-layer="344" from-port="0" to-layer="345" to-port="1" />
<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="360" to-port="0" />
<edge from-layer="348" from-port="0" to-layer="349" to-port="0" />
<edge from-layer="349" from-port="1" to-layer="352" to-port="0" />
<edge from-layer="350" from-port="0" to-layer="351" to-port="0" />
<edge from-layer="351" from-port="1" to-layer="352" to-port="1" />
<edge from-layer="352" from-port="2" to-layer="354" to-port="0" />
<edge from-layer="353" from-port="0" to-layer="354" to-port="1" />
<edge from-layer="354" from-port="2" to-layer="355" to-port="0" />
<edge from-layer="355" from-port="1" to-layer="356" to-port="1" />
<edge from-layer="356" from-port="2" to-layer="357" to-port="0" />
<edge from-layer="357" from-port="2" to-layer="359" to-port="0" />
<edge from-layer="358" from-port="0" to-layer="359" to-port="1" />
<edge from-layer="359" from-port="2" to-layer="360" to-port="1" />
<edge from-layer="360" from-port="2" to-layer="361" to-port="0" />
<edge from-layer="361" from-port="1" to-layer="376" 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="366" to-port="0" />
<edge from-layer="364" from-port="0" to-layer="365" to-port="0" />
<edge from-layer="365" from-port="1" to-layer="366" to-port="1" />
<edge from-layer="366" from-port="2" to-layer="368" to-port="0" />
<edge from-layer="367" from-port="0" to-layer="368" to-port="1" />
<edge from-layer="368" from-port="2" to-layer="369" to-port="0" />
<edge from-layer="369" from-port="1" to-layer="370" to-port="1" />
<edge from-layer="370" from-port="2" to-layer="372" to-port="0" />
<edge from-layer="371" from-port="0" to-layer="372" to-port="1" />
<edge from-layer="372" from-port="2" to-layer="373" to-port="0" />
<edge from-layer="373" from-port="2" to-layer="375" to-port="0" />
<edge from-layer="374" from-port="0" to-layer="375" to-port="1" />
<edge from-layer="375" from-port="2" to-layer="376" to-port="1" />
<edge from-layer="376" from-port="2" to-layer="378" to-port="0" />
<edge from-layer="377" from-port="0" 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="389" 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="385" to-port="0" />
<edge from-layer="383" from-port="0" to-layer="384" to-port="0" />
<edge from-layer="384" from-port="1" to-layer="385" to-port="1" />
<edge from-layer="385" from-port="2" to-layer="387" to-port="0" />
<edge from-layer="386" from-port="0" to-layer="387" to-port="1" />
<edge from-layer="387" from-port="2" to-layer="388" to-port="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="1" />
<edge from-layer="392" from-port="2" to-layer="422" to-port="0" />
<edge from-layer="392" from-port="2" to-layer="394" to-port="0" />
<edge from-layer="393" from-port="0" to-layer="394" to-port="1" />
<edge from-layer="394" from-port="2" to-layer="396" to-port="0" />
<edge from-layer="395" from-port="0" to-layer="396" to-port="1" />
<edge from-layer="396" from-port="2" to-layer="398" to-port="0" />
<edge from-layer="397" from-port="0" to-layer="398" to-port="1" />
<edge from-layer="398" from-port="2" to-layer="407" to-port="0" />
<edge from-layer="399" from-port="0" to-layer="400" to-port="0" />
<edge from-layer="400" from-port="1" to-layer="403" to-port="0" />
<edge from-layer="401" from-port="0" to-layer="402" to-port="0" />
<edge from-layer="402" from-port="1" 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="406" to-port="0" />
<edge from-layer="406" from-port="1" to-layer="407" to-port="1" />
<edge from-layer="407" from-port="2" to-layer="409" to-port="0" />
<edge from-layer="408" from-port="0" to-layer="409" to-port="1" />
<edge from-layer="409" from-port="2" to-layer="410" to-port="0" />
<edge from-layer="410" from-port="1" to-layer="419" to-port="0" />
<edge from-layer="411" from-port="0" to-layer="412" to-port="0" />
<edge from-layer="412" from-port="1" to-layer="415" to-port="0" />
<edge from-layer="413" from-port="0" to-layer="414" to-port="0" />
<edge from-layer="414" from-port="1" 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="418" 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="421" to-port="0" />
<edge from-layer="420" from-port="0" to-layer="421" to-port="1" />
<edge from-layer="421" from-port="2" to-layer="422" to-port="1" />
<edge from-layer="422" from-port="2" to-layer="424" to-port="0" />
<edge from-layer="423" from-port="0" to-layer="424" to-port="1" />
<edge from-layer="424" from-port="2" to-layer="426" to-port="0" />
<edge from-layer="425" from-port="0" to-layer="426" to-port="1" />
<edge from-layer="426" from-port="2" to-layer="428" to-port="0" />
<edge from-layer="427" from-port="0" to-layer="428" to-port="1" />
<edge from-layer="428" from-port="2" to-layer="429" to-port="0" />
<edge from-layer="429" from-port="2" to-layer="430" to-port="0" />
</edges>
<rt_info>
<Runtime_version value="2024.5.0-16901-32aaa2fbd96" />
<conversion_parameters>
<framework value="pytorch" />
<is_python_object value="True" />
</conversion_parameters>
<nncf>
<friendly_names_were_updated value="True" />
<weight_compression>
<advanced_parameters value="{'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" />
<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>
<optimum_intel_version value="1.20.0.dev0+2559620" />
<optimum_version value="1.23.1" />
<pytorch_version value="2.5.0" />
<transformers_version value="4.45.2" />
</optimum>
</rt_info>
</net>