distil-whisper-large-v3-int8-ov / openvino_decoder_with_past_model.xml
openvino-ci's picture
Upload folder using huggingface_hub
b45f2a0 verified
<?xml version="1.0"?>
<net name="Model6" version="11">
<layers>
<layer id="10" name="decoder_input_ids" type="Parameter" version="opset1">
<data shape="?,1" element_type="i64" />
<output>
<port id="0" precision="I64" names="input_ids">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="9" name="encoder_outputs" type="Parameter" version="opset1">
<data shape="?,?,1280" element_type="f32" />
<output>
<port id="0" precision="FP32" names="encoder_hidden_states">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="8" name="Parameter_34544" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.0.decoder.key">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="7" name="Parameter_34543" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.0.decoder.value">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="6" name="Parameter_34542" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.0.encoder.key">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="5" name="Parameter_34541" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.0.encoder.value">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="4" name="Parameter_34548" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.1.decoder.key">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="3" name="Parameter_34547" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.1.decoder.value">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="2" name="Parameter_34546" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.1.encoder.key">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="1" name="Parameter_34545" type="Parameter" version="opset1">
<data shape="?,20,?,64" element_type="f32" />
<output>
<port id="0" precision="FP32" names="past_key_values.1.encoder.value">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="0" name="cache_position" type="Parameter" version="opset1">
<data shape="?" element_type="i64" />
<output>
<port id="0" precision="I64" names="cache_position">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="11" name="self.model.model.decoder.embed_tokens.weight" type="Const" version="opset1">
<data element_type="u8" shape="51866, 1280" offset="0" size="66388480" />
<output>
<port id="0" precision="U8">
<dim>51866</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="12" name="Convert_53341" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>51866</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>51866</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="13" name="self.model.model.decoder.embed_tokens.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="51866, 1" offset="66388480" size="51866" />
<output>
<port id="0" precision="U8">
<dim>51866</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="14" name="Convert_53344" type="Convert" version="opset1">
<data destination_type="f16" />
<input>
<port id="0" precision="U8">
<dim>51866</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="FP16">
<dim>51866</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="15" name="self.model.model.decoder.embed_tokens.weight/zero_point/subtract" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>51866</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>51866</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>51866</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="16" name="self.model.model.decoder.embed_tokens.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="51866, 1" offset="66440346" size="103732" />
<output>
<port id="0" precision="FP16">
<dim>51866</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="17" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP16">
<dim>51866</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP16">
<dim>51866</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP16">
<dim>51866</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="18" name="self.model.model.decoder.embed_tokens.weight/fq_weights_0/convert" type="Convert" version="opset1">
<data destination_type="f32" />
<input>
<port id="0" precision="FP16">
<dim>51866</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>51866</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="19" name="__module.model.model.decoder/prim::ListConstruct" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="66544078" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="20" 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="65">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="21" 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="22" name="__module.model.model.decoder.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66544094" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="23" name="__module.model.model.decoder.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="FP32">
<dim>51866</dim>
<dim>1280</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
<dim>1</dim>
</port>
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="FP32" names="67,inputs_embeds">
<dim>-1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="24" name="self.model.model.decoder.embed_positions.weight" type="Const" version="opset1">
<data element_type="u8" shape="448, 1280" offset="66544098" size="573440" />
<output>
<port id="0" precision="U8">
<dim>448</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="25" name="Convert_53528" 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="26" name="self.model.model.decoder.embed_positions.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="448, 1" offset="67117538" size="448" />
<output>
<port id="0" precision="U8">
<dim>448</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="27" name="Convert_53531" 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="28" 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="29" name="self.model.model.decoder.embed_positions.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="448, 1" offset="67117986" size="896" />
<output>
<port id="0" precision="FP16">
<dim>448</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="30" 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="31" 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="32" name="42" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67118882" size="8" />
<output>
<port id="0" precision="I64" names="42" />
</output>
</layer>
<layer id="33" name="__module.model.model.decoder/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="I64">
<dim>-1</dim>
</port>
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="I64" names="71,position_ids">
<dim>1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="34" name="__module.model.model.decoder.embed_positions/aten::index/Convert" type="Convert" version="opset1">
<data destination_type="i32" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="35" name="__module.model.model.decoder.embed_positions/aten::index/Constant" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66544094" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="36" 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="74,75,positions,positions.1">
<dim>1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="37" name="__module.model.model.decoder/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="76,input.1">
<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" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="39" 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="40" name="Constant_39166" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="67118894" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="41" 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="42" name="Constant_39167" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="67124014" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="43" 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="110,hidden_states.1">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="44" name="Constant_39086" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="67129134" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="45" name="Convert_53418" 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="46" name="Constant_39086/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="68767534" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="47" name="Convert_53421" 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="48" name="Constant_39086/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="49" name="Constant_39086/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="68768814" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="50" name="Constant_39086/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="51" name="Constant_39086/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="52" name="Multiply_39069" 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="53" name="Constant_39168" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="68771374" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="54" 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="120,tensor.1">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="55" name="Constant_39768" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="56" 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="122">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="57" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="58" 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="123">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="59" name="self.model.model.decoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="68776542" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="60" name="Convert_53407" 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="61" 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="70414942" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="62" name="Convert_53410" 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="63" 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="64" 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="70416222" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="65" 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="66" 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="67" 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="126,tensor.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="68" name="Constant_39769" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="69" 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="128">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="70" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="71" 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="129">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="72" name="__module.model.model.decoder.layers.0.self_attn/aten::cat/Concat" type="Concat" version="opset1">
<data axis="-2" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="present.0.decoder.key">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="73" 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="146,attn_weights.1">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="74" name="Constant_39169" type="Const" version="opset1">
<data element_type="f32" shape="1, 1" offset="70418782" size="4" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="75" name="__module.model.model.decoder/aten::arange/Constant" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66544094" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="76" name="ShapeOf_39578" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="77" name="Constant_39579" type="Const" version="opset1">
<data element_type="i64" shape="" offset="70418786" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="78" name="Constant_39580" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67118882" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="79" name="Gather_39581" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" names="78" />
</output>
</layer>
<layer id="80" name="ShapeOf_39586" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="81" name="Constant_39587" type="Const" version="opset1">
<data element_type="i64" shape="" offset="70418794" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="82" name="Constant_39588" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67118882" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="83" name="Gather_39589" 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="80" />
</output>
</layer>
<layer id="84" name="__module.model.model.decoder/aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="I64" names="82" />
</output>
</layer>
<layer id="85" name="__module.model.model.decoder/aten::add/Multiply_2" type="Const" version="opset1">
<data element_type="i64" shape="" offset="70418794" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="86" name="__module.model.model.decoder/aten::add/Add_2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="I64" names="83,85" />
</output>
</layer>
<layer id="87" name="__module.model.model.decoder/aten::arange/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="" offset="70418802" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="88" name="__module.model.model.decoder/aten::arange/Range" type="Range" version="opset4">
<data output_type="f32" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="FP32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="89" 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="89">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="90" name="Constant_32802" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="70418806" size="16" />
<output>
<port id="0" precision="I64" names="90">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="91" name="__module.model.model.decoder/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="I64">
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="I64" names="91">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="92" name="__module.model.model.decoder/aten::gt/Greater" type="Greater" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>-1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="BOOL" names="92">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="93" 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="94" name="Multiply_38724" type="Multiply" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="95" name="ShapeOf_38725" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="96" name="Constant_39592" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="97" name="Reshape_39593" 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="98" name="Constant_32788" type="Const" version="opset1">
<data element_type="i32" shape="" offset="66544094" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="99" name="Unsqueeze_32789" 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="100" 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="101" name="Maximum_38726" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>2</dim>
</port>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="102" name="__module.model.model.decoder/aten::mul_/Multiply" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="88,causal_mask.1">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="103" 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="94">
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="104" name="48" type="Const" version="opset1">
<data element_type="i64" shape="" offset="70418794" size="8" />
<output>
<port id="0" precision="I64" names="48" />
</output>
</layer>
<layer id="105" 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="95,96,97">
<dim>1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="106" name="ShapeOf_39570" 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="107" name="Constant_39571" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67118882" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="108" name="Constant_39572" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67118882" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="109" name="Gather_39573" 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="115,230,86">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="110" name="Constant_38168" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="111" name="Constant_38170" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="112" name="Constant_38172" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="113" 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="114" 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="148,149,150,260,261,262,99,attention_mask">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="115" name="Constant_33249" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="67118882" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="116" name="Constant_39600" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="117" name="Reshape_39601" 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="118" name="Constant_39603" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="119" name="Constant_39604" type="Const" version="opset1">
<data element_type="i64" shape="" offset="67118882" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="120" name="Gather_39605" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="121" name="Add_39606" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64" names="147,259">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="122" name="Constant_33252" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418794" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="123" name="__module.model.model.decoder/aten::slice/Reshape_1" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="70418822" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="124" 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="151,263,causal_mask,causal_mask.5">
<dim>-1</dim>
<dim>1</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="125" 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="152,input.3">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="126" 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="153,input.5">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="127" name="self.model.model.decoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="70418830" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="128" name="Convert_53396" 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="129" 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="72057230" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="130" name="Convert_53399" 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="131" 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="132" 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="72058510" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="133" 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="134" 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="135" 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="136" name="Constant_39170" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="72061070" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="137" 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="133,tensor.5">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="138" name="Constant_39770" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="139" 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="135">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="140" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="141" 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="136">
<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::cat/Concat_1" type="Concat" version="opset1">
<data axis="-2" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="present.0.decoder.value">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="143" 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="155,attn_output.1">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="144" name="__module.model.model.decoder.layers.0.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="145" 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="156,attn_output.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="146" name="Constant_39771" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="72066190" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="147" 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="158">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="148" name="self.model.model.decoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="72066214" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="149" name="Convert_53429" 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="150" 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="73704614" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="151" name="Convert_53432" 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="152" 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="153" 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="73705894" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="154" 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="155" 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="156" 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="157" name="Constant_39171" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="73708454" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="158" 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="161,163,input.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="159" 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="167,residual.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="160" 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="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="161" 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="162" name="Constant_39172" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="73713574" 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/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="164" name="Constant_39173" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="73718694" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="165" 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="171,hidden_states.5">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="166" name="Constant_39089" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="73723814" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="167" name="Convert_53440" 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="168" name="Constant_39089/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="75362214" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="169" name="Convert_53443" 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="170" name="Constant_39089/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="171" name="Constant_39089/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="75363494" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="172" name="Constant_39089/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="173" name="Constant_39089/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="174" name="Multiply_39073" 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="175" name="Constant_39174" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="75366054" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="176" 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="179,tensor.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="177" name="Constant_39772" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="178" 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="181">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="179" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="180" 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="182">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="181" 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="185,input.9">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="182" 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="186,input.11">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="183" 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="188,attn_output.5">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="184" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="185" name="__module.model.model.decoder.layers.0.encoder_attn/aten::transpose/Transpose_2" 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="189,attn_output.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="186" name="Constant_39773" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="75371174" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="187" 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="191">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="188" name="self.model.model.decoder.layers.0.encoder_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="75371198" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="189" name="Convert_53451" 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="190" 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="77009598" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="191" name="Convert_53454" 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="192" 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="193" 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="77010878" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="194" 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="195" 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="196" 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="197" name="Constant_39175" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="77013438" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="198" 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="194,input.13">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="199" 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="196,residual.5">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="200" 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="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="201" 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="202" name="Constant_39176" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="77018558" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="203" 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="204" name="Constant_39177" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="77023678" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="205" 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="200">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="206" name="self.model.model.decoder.layers.0.fc1.weight" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1280" offset="77028798" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="207" name="Convert_53352" 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="208" name="self.model.model.decoder.layers.0.fc1.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1" offset="83582398" size="5120" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="209" name="Convert_53355" 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="210" 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="211" name="self.model.model.decoder.layers.0.fc1.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="5120, 1" offset="83587518" size="10240" />
<output>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="212" 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="213" 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="214" 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="215" name="Constant_39178" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 5120" offset="83597758" size="20480" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="216" 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="203">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="217" 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="204,input.15">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="218" name="self.model.model.decoder.layers.0.fc2.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 5120" offset="83618238" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="219" name="Convert_53363" 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="220" name="self.model.model.decoder.layers.0.fc2.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="90171838" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="221" name="Convert_53366" 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="222" 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="223" name="self.model.model.decoder.layers.0.fc2.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="90173118" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="224" 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="225" 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="226" 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="227" name="Constant_39179" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="90175678" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="228" 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="208,input.17">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="229" 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="210,212,residual.7">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="230" 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="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="231" 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="232" name="Constant_39180" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="90180798" 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.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="234" name="Constant_39181" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="90185918" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="235" 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="225,hidden_states.11">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="236" name="self.model.model.decoder.layers.1.self_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="90191038" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="237" name="Convert_53462" 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="238" 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="91829438" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="239" name="Convert_53465" 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="240" 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="241" 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="91830718" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="242" 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="243" 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="244" 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="245" name="Constant_39182" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="91833278" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="246" 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="248,tensor.13">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="247" name="Constant_39774" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="248" 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="250">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="249" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="250" 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="251">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="251" name="__module.model.model.decoder.layers.1.self_attn/aten::cat/Concat" type="Concat" version="opset1">
<data axis="-2" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="present.1.decoder.value">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="253" name="self.model.model.decoder.layers.1.self_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="91838398" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="254" name="Convert_53473" 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="255" 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="93476798" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="256" name="Convert_53476" 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="257" 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="258" 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="93478078" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="259" 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="260" 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="261" 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="241,tensor.11">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="262" name="Constant_39775" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="263" 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="243">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="264" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="265" 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="244">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="266" name="__module.model.model.decoder.layers.1.self_attn/aten::cat/Concat_1" type="Concat" version="opset1">
<data axis="-2" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="present.1.decoder.key">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="270" name="Constant_39092" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="93480638" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="271" name="Convert_53484" 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="272" name="Constant_39092/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="95119038" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="273" name="Convert_53487" 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="274" name="Constant_39092/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="275" name="Constant_39092/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="95120318" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="276" name="Constant_39092/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="277" name="Constant_39092/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="278" name="Multiply_39077" 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="279" name="Constant_39183" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="95122878" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="280" 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="235,tensor.9">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="281" name="Constant_39776" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="282" 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="237">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="283" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="284" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="238">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="285" 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="258,attn_weights">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="286" 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="264,input.19">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="287" 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="265,input.21">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="288" 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="267,attn_output.9">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="289" name="__module.model.model.decoder.layers.1.self_attn/aten::transpose/Constant_4" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="290" 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="268,attn_output.11">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="291" name="Constant_39777" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="72066190" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="292" 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="270">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="293" name="self.model.model.decoder.layers.1.self_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="95127998" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="294" name="Convert_53495" 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="295" 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="96766398" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="296" name="Convert_53498" 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="297" 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="298" 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="96767678" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="299" 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="300" 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="301" 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="302" name="Constant_39184" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="96770238" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="303" name="__module.model.model.decoder.layers.1.self_attn.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="273,275,input.23">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="304" 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="279,residual.9">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="305" 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="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="306" 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="307" name="Constant_39185" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="96775358" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="308" 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="309" name="Constant_39186" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="96780478" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="310" 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="283,hidden_states.15">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="311" name="Constant_39095" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="96785598" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="312" name="Convert_53506" 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="313" name="Constant_39095/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="98423998" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="314" name="Convert_53509" 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="315" name="Constant_39095/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="316" name="Constant_39095/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="98425278" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="317" name="Constant_39095/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="318" name="Constant_39095/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="319" name="Multiply_39081" 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="320" name="Constant_39187" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="98427838" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="321" 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="291,tensor">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="322" name="Constant_39778" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="68776494" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="323" 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="293">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="324" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="325" 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="294">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="326" 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="297,input.25">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="327" 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="298,input.27">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="328" 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="300,attn_output.13">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="329" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Constant_2" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="68776526" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="330" name="__module.model.model.decoder.layers.1.encoder_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="301,attn_output">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="331" name="Constant_39779" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="75371174" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="332" name="__module.model.model.decoder.layers.1.encoder_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>20</dim>
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="303">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="333" name="self.model.model.decoder.layers.1.encoder_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1280" offset="98432958" size="1638400" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="334" name="Convert_53517" 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="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="100071358" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="336" name="Convert_53520" 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="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="338" 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="100072638" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="339" 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="340" 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="341" 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="342" name="Constant_39188" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="100075198" 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.out_proj/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="306,input.29">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="344" name="__module.model.model.decoder.layers.1/aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="308,residual">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="345" 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="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="346" 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="347" name="Constant_39189" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="100080318" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="348" 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="349" name="Constant_39190" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="100085438" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="350" name="__module.model.model.decoder.layers.1.final_layer_norm/aten::layer_norm/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="312">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="351" name="self.model.model.decoder.layers.1.fc1.weight" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1280" offset="100090558" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="352" name="Convert_53374" 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="353" name="self.model.model.decoder.layers.1.fc1.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="5120, 1" offset="106644158" size="5120" />
<output>
<port id="0" precision="U8">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="354" name="Convert_53377" 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="355" 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="356" name="self.model.model.decoder.layers.1.fc1.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="5120, 1" offset="106649278" size="10240" />
<output>
<port id="0" precision="FP16">
<dim>5120</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="357" 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="358" 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="359" 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="360" name="Constant_39191" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 5120" offset="106659518" size="20480" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="361" name="__module.model.model.decoder.layers.1.fc1/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="315">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="362" name="__module.model.model.decoder.layers.1.activation_fn/aten::gelu/Gelu" type="Gelu" version="opset7">
<data approximation_mode="ERF" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="316,input.31">
<dim>-1</dim>
<dim>-1</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="363" name="self.model.model.decoder.layers.1.fc2.weight" type="Const" version="opset1">
<data element_type="u8" shape="1280, 5120" offset="106679998" size="6553600" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>5120</dim>
</port>
</output>
</layer>
<layer id="364" name="Convert_53385" 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="365" name="self.model.model.decoder.layers.1.fc2.weight/zero_point" type="Const" version="opset1">
<data element_type="u8" shape="1280, 1" offset="113233598" size="1280" />
<output>
<port id="0" precision="U8">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="366" name="Convert_53388" 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="367" 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="368" name="self.model.model.decoder.layers.1.fc2.weight/scale" type="Const" version="opset1">
<data element_type="f16" shape="1280, 1" offset="113234878" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1280</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="369" 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="370" 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="371" 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="372" name="Constant_39192" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="113237438" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="373" name="__module.model.model.decoder.layers.1.fc2/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="320,input">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="374" name="__module.model.model.decoder.layers.1/aten::add/Add_2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="322,324">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="375" name="__module.model.model.decoder.layer_norm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="67118890" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="376" 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="377" name="Constant_39193" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="113242558" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="378" 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="379" name="Constant_39194" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 1280" offset="113247678" size="5120" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="380" 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="330,332,338">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="381" name="__module.model.proj_out/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>1280</dim>
</port>
<port id="1" precision="FP32">
<dim>51866</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="logits">
<dim>-1</dim>
<dim>-1</dim>
<dim>51866</dim>
</port>
</output>
</layer>
<layer id="382" name="Result_34532" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>51866</dim>
</port>
</input>
</layer>
<layer id="269" name="Result_34536" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
</layer>
<layer id="268" name="Result_34535" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
</layer>
<layer id="267" name="Result_34538" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
</layer>
<layer id="252" name="Result_34537" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>20</dim>
<dim>-1</dim>
<dim>64</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="91" to-port="0" />
<edge from-layer="0" from-port="0" to-layer="33" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="328" to-port="1" />
<edge from-layer="2" from-port="0" to-layer="326" to-port="1" />
<edge from-layer="3" from-port="0" to-layer="251" to-port="0" />
<edge from-layer="4" from-port="0" to-layer="266" to-port="0" />
<edge from-layer="5" from-port="0" to-layer="183" to-port="1" />
<edge from-layer="6" from-port="0" to-layer="181" to-port="1" />
<edge from-layer="7" from-port="0" to-layer="142" to-port="0" />
<edge from-layer="8" from-port="0" to-layer="76" to-port="0" />
<edge from-layer="8" from-port="0" to-layer="72" to-port="0" />
<edge from-layer="10" from-port="0" to-layer="20" to-port="0" />
<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
<edge from-layer="12" from-port="1" to-layer="15" to-port="0" />
<edge from-layer="13" from-port="0" to-layer="14" to-port="0" />
<edge from-layer="14" from-port="1" to-layer="15" to-port="1" />
<edge from-layer="15" from-port="2" to-layer="17" to-port="0" />
<edge from-layer="16" from-port="0" to-layer="17" to-port="1" />
<edge from-layer="17" from-port="2" to-layer="18" to-port="0" />
<edge from-layer="18" from-port="1" to-layer="381" to-port="1" />
<edge from-layer="18" from-port="1" to-layer="23" to-port="0" />
<edge from-layer="19" from-port="0" to-layer="20" to-port="1" />
<edge from-layer="20" from-port="2" to-layer="21" to-port="0" />
<edge from-layer="21" from-port="1" to-layer="80" to-port="0" />
<edge from-layer="21" from-port="1" to-layer="23" to-port="1" />
<edge from-layer="22" from-port="0" to-layer="23" to-port="2" />
<edge from-layer="23" from-port="3" to-layer="37" to-port="0" />
<edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
<edge from-layer="25" from-port="1" to-layer="28" to-port="0" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="0" />
<edge from-layer="27" from-port="1" to-layer="28" to-port="1" />
<edge from-layer="28" from-port="2" to-layer="30" to-port="0" />
<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
<edge from-layer="30" from-port="2" to-layer="31" to-port="0" />
<edge from-layer="31" from-port="1" to-layer="36" to-port="0" />
<edge from-layer="32" from-port="0" to-layer="33" to-port="1" />
<edge from-layer="32" from-port="0" to-layer="103" to-port="1" />
<edge from-layer="33" from-port="2" to-layer="34" to-port="0" />
<edge from-layer="34" from-port="1" to-layer="36" to-port="1" />
<edge from-layer="35" from-port="0" to-layer="36" to-port="2" />
<edge from-layer="36" from-port="3" to-layer="37" to-port="1" />
<edge from-layer="37" from-port="2" to-layer="159" to-port="0" />
<edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
<edge from-layer="41" from-port="2" to-layer="43" to-port="0" />
<edge from-layer="42" from-port="0" to-layer="43" to-port="1" />
<edge from-layer="43" from-port="2" to-layer="106" to-port="0" />
<edge from-layer="43" from-port="2" to-layer="135" to-port="0" />
<edge from-layer="43" from-port="2" to-layer="67" to-port="0" />
<edge from-layer="43" from-port="2" to-layer="52" to-port="0" />
<edge from-layer="44" from-port="0" to-layer="45" to-port="0" />
<edge from-layer="45" from-port="1" to-layer="48" to-port="0" />
<edge from-layer="46" from-port="0" to-layer="47" to-port="0" />
<edge from-layer="47" from-port="1" to-layer="48" to-port="1" />
<edge from-layer="48" from-port="2" to-layer="50" to-port="0" />
<edge from-layer="49" from-port="0" to-layer="50" to-port="1" />
<edge from-layer="50" from-port="2" to-layer="51" to-port="0" />
<edge from-layer="51" from-port="1" to-layer="52" to-port="1" />
<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
<edge from-layer="54" from-port="2" to-layer="56" to-port="0" />
<edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
<edge from-layer="56" from-port="2" to-layer="58" to-port="0" />
<edge from-layer="57" from-port="0" to-layer="58" to-port="1" />
<edge from-layer="58" from-port="2" to-layer="73" to-port="0" />
<edge from-layer="59" from-port="0" to-layer="60" to-port="0" />
<edge from-layer="60" from-port="1" to-layer="63" to-port="0" />
<edge from-layer="61" from-port="0" to-layer="62" to-port="0" />
<edge from-layer="62" from-port="1" to-layer="63" to-port="1" />
<edge from-layer="63" from-port="2" to-layer="65" to-port="0" />
<edge from-layer="64" from-port="0" to-layer="65" to-port="1" />
<edge from-layer="65" from-port="2" to-layer="66" to-port="0" />
<edge from-layer="66" from-port="1" to-layer="67" to-port="1" />
<edge from-layer="67" from-port="2" to-layer="69" to-port="0" />
<edge from-layer="68" from-port="0" to-layer="69" to-port="1" />
<edge from-layer="69" from-port="2" to-layer="71" to-port="0" />
<edge from-layer="70" from-port="0" to-layer="71" to-port="1" />
<edge from-layer="71" from-port="2" to-layer="72" to-port="1" />
<edge from-layer="72" from-port="2" to-layer="73" to-port="1" />
<edge from-layer="72" from-port="2" to-layer="269" to-port="0" />
<edge from-layer="73" from-port="2" to-layer="125" to-port="0" />
<edge from-layer="74" from-port="0" to-layer="94" to-port="0" />
<edge from-layer="75" from-port="0" to-layer="88" to-port="0" />
<edge from-layer="76" from-port="1" to-layer="79" to-port="0" />
<edge from-layer="77" from-port="0" to-layer="79" to-port="1" />
<edge from-layer="78" from-port="0" to-layer="79" to-port="2" />
<edge from-layer="79" from-port="3" to-layer="84" to-port="0" />
<edge from-layer="79" from-port="3" to-layer="117" 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="97" to-port="0" />
<edge from-layer="83" from-port="3" to-layer="84" to-port="1" />
<edge from-layer="84" from-port="2" to-layer="86" to-port="0" />
<edge from-layer="85" from-port="0" to-layer="86" to-port="1" />
<edge from-layer="86" from-port="2" to-layer="99" to-port="0" />
<edge from-layer="86" from-port="2" to-layer="88" to-port="1" />
<edge from-layer="87" from-port="0" to-layer="88" to-port="2" />
<edge from-layer="88" from-port="3" to-layer="89" to-port="0" />
<edge from-layer="89" from-port="1" to-layer="92" to-port="0" />
<edge from-layer="90" from-port="0" to-layer="91" to-port="1" />
<edge from-layer="91" from-port="2" to-layer="92" to-port="1" />
<edge from-layer="92" from-port="2" to-layer="93" to-port="0" />
<edge from-layer="93" from-port="1" to-layer="94" to-port="1" />
<edge from-layer="94" from-port="2" to-layer="95" to-port="0" />
<edge from-layer="94" from-port="2" to-layer="102" to-port="0" />
<edge from-layer="95" from-port="1" to-layer="101" to-port="0" />
<edge from-layer="96" from-port="0" to-layer="97" to-port="1" />
<edge from-layer="97" from-port="2" to-layer="100" to-port="0" />
<edge from-layer="98" from-port="0" to-layer="99" to-port="1" />
<edge from-layer="99" from-port="2" to-layer="100" to-port="1" />
<edge from-layer="100" from-port="2" 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="2" to-layer="105" to-port="0" />
<edge from-layer="104" from-port="0" to-layer="105" to-port="1" />
<edge from-layer="105" from-port="2" to-layer="114" to-port="0" />
<edge from-layer="106" from-port="1" to-layer="120" to-port="0" />
<edge from-layer="106" from-port="1" to-layer="109" to-port="0" />
<edge from-layer="107" from-port="0" to-layer="109" to-port="1" />
<edge from-layer="108" from-port="0" to-layer="109" to-port="2" />
<edge from-layer="109" from-port="3" to-layer="113" to-port="0" />
<edge from-layer="110" from-port="0" to-layer="113" to-port="1" />
<edge from-layer="111" from-port="0" to-layer="113" to-port="2" />
<edge from-layer="112" from-port="0" to-layer="113" to-port="3" />
<edge from-layer="113" from-port="4" to-layer="114" to-port="1" />
<edge from-layer="114" from-port="2" to-layer="124" to-port="0" />
<edge from-layer="115" from-port="0" to-layer="124" to-port="1" />
<edge from-layer="116" from-port="0" to-layer="117" to-port="1" />
<edge from-layer="117" from-port="2" to-layer="121" 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="121" to-port="1" />
<edge from-layer="121" from-port="2" to-layer="124" to-port="2" />
<edge from-layer="122" from-port="0" to-layer="124" to-port="3" />
<edge from-layer="123" from-port="0" to-layer="124" to-port="4" />
<edge from-layer="124" from-port="5" to-layer="286" to-port="1" />
<edge from-layer="124" from-port="5" to-layer="125" to-port="1" />
<edge from-layer="125" from-port="2" to-layer="126" to-port="0" />
<edge from-layer="126" from-port="1" to-layer="143" to-port="0" />
<edge from-layer="127" from-port="0" to-layer="128" to-port="0" />
<edge from-layer="128" from-port="1" to-layer="131" to-port="0" />
<edge from-layer="129" from-port="0" to-layer="130" to-port="0" />
<edge from-layer="130" from-port="1" to-layer="131" to-port="1" />
<edge from-layer="131" from-port="2" to-layer="133" to-port="0" />
<edge from-layer="132" from-port="0" to-layer="133" to-port="1" />
<edge from-layer="133" from-port="2" to-layer="134" to-port="0" />
<edge from-layer="134" from-port="1" to-layer="135" to-port="1" />
<edge from-layer="135" from-port="2" to-layer="137" to-port="0" />
<edge from-layer="136" from-port="0" to-layer="137" to-port="1" />
<edge from-layer="137" from-port="2" to-layer="139" to-port="0" />
<edge from-layer="138" from-port="0" to-layer="139" to-port="1" />
<edge from-layer="139" from-port="2" to-layer="141" to-port="0" />
<edge from-layer="140" from-port="0" to-layer="141" to-port="1" />
<edge from-layer="141" from-port="2" to-layer="142" to-port="1" />
<edge from-layer="142" from-port="2" to-layer="268" to-port="0" />
<edge from-layer="142" from-port="2" 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="147" to-port="0" />
<edge from-layer="146" from-port="0" to-layer="147" to-port="1" />
<edge from-layer="147" from-port="2" to-layer="156" 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="152" to-port="0" />
<edge from-layer="150" from-port="0" to-layer="151" to-port="0" />
<edge from-layer="151" from-port="1" to-layer="152" to-port="1" />
<edge from-layer="152" from-port="2" to-layer="154" to-port="0" />
<edge from-layer="153" from-port="0" to-layer="154" to-port="1" />
<edge from-layer="154" from-port="2" to-layer="155" to-port="0" />
<edge from-layer="155" from-port="1" to-layer="156" to-port="1" />
<edge from-layer="156" from-port="2" to-layer="158" to-port="0" />
<edge from-layer="157" from-port="0" to-layer="158" to-port="1" />
<edge from-layer="158" from-port="2" to-layer="159" to-port="1" />
<edge from-layer="159" from-port="2" to-layer="199" to-port="0" />
<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="165" to-port="0" />
<edge from-layer="164" from-port="0" to-layer="165" to-port="1" />
<edge from-layer="165" from-port="2" to-layer="174" 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="170" to-port="0" />
<edge from-layer="168" from-port="0" to-layer="169" to-port="0" />
<edge from-layer="169" from-port="1" to-layer="170" to-port="1" />
<edge from-layer="170" from-port="2" to-layer="172" to-port="0" />
<edge from-layer="171" from-port="0" to-layer="172" to-port="1" />
<edge from-layer="172" from-port="2" to-layer="173" to-port="0" />
<edge from-layer="173" from-port="1" 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="180" to-port="0" />
<edge from-layer="179" from-port="0" to-layer="180" to-port="1" />
<edge from-layer="180" from-port="2" to-layer="181" to-port="0" />
<edge from-layer="181" from-port="2" to-layer="182" to-port="0" />
<edge from-layer="182" from-port="1" to-layer="183" to-port="0" />
<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="187" to-port="0" />
<edge from-layer="186" from-port="0" to-layer="187" to-port="1" />
<edge from-layer="187" from-port="2" to-layer="196" to-port="0" />
<edge from-layer="188" from-port="0" to-layer="189" to-port="0" />
<edge from-layer="189" from-port="1" to-layer="192" to-port="0" />
<edge from-layer="190" from-port="0" to-layer="191" to-port="0" />
<edge from-layer="191" from-port="1" to-layer="192" to-port="1" />
<edge from-layer="192" from-port="2" to-layer="194" to-port="0" />
<edge from-layer="193" from-port="0" to-layer="194" to-port="1" />
<edge from-layer="194" from-port="2" to-layer="195" to-port="0" />
<edge from-layer="195" from-port="1" to-layer="196" to-port="1" />
<edge from-layer="196" from-port="2" to-layer="198" to-port="0" />
<edge from-layer="197" from-port="0" to-layer="198" to-port="1" />
<edge from-layer="198" from-port="2" to-layer="199" to-port="1" />
<edge from-layer="199" from-port="2" to-layer="201" to-port="0" />
<edge from-layer="199" from-port="2" to-layer="229" to-port="0" />
<edge from-layer="200" from-port="0" to-layer="201" to-port="1" />
<edge from-layer="201" from-port="2" to-layer="203" to-port="0" />
<edge from-layer="202" from-port="0" to-layer="203" to-port="1" />
<edge from-layer="203" from-port="2" to-layer="205" to-port="0" />
<edge from-layer="204" from-port="0" to-layer="205" to-port="1" />
<edge from-layer="205" from-port="2" to-layer="214" to-port="0" />
<edge from-layer="206" from-port="0" to-layer="207" to-port="0" />
<edge from-layer="207" from-port="1" to-layer="210" to-port="0" />
<edge from-layer="208" from-port="0" to-layer="209" to-port="0" />
<edge from-layer="209" from-port="1" to-layer="210" to-port="1" />
<edge from-layer="210" from-port="2" to-layer="212" to-port="0" />
<edge from-layer="211" from-port="0" to-layer="212" to-port="1" />
<edge from-layer="212" from-port="2" to-layer="213" to-port="0" />
<edge from-layer="213" from-port="1" to-layer="214" to-port="1" />
<edge from-layer="214" from-port="2" to-layer="216" to-port="0" />
<edge from-layer="215" from-port="0" to-layer="216" to-port="1" />
<edge from-layer="216" from-port="2" to-layer="217" to-port="0" />
<edge from-layer="217" from-port="1" to-layer="226" 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="222" to-port="0" />
<edge from-layer="220" from-port="0" to-layer="221" to-port="0" />
<edge from-layer="221" from-port="1" to-layer="222" to-port="1" />
<edge from-layer="222" from-port="2" to-layer="224" to-port="0" />
<edge from-layer="223" from-port="0" to-layer="224" to-port="1" />
<edge from-layer="224" from-port="2" to-layer="225" to-port="0" />
<edge from-layer="225" from-port="1" to-layer="226" to-port="1" />
<edge from-layer="226" from-port="2" to-layer="228" to-port="0" />
<edge from-layer="227" from-port="0" to-layer="228" to-port="1" />
<edge from-layer="228" from-port="2" to-layer="229" to-port="1" />
<edge from-layer="229" from-port="2" to-layer="304" to-port="0" />
<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="235" to-port="0" />
<edge from-layer="234" from-port="0" to-layer="235" to-port="1" />
<edge from-layer="235" from-port="2" to-layer="261" to-port="0" />
<edge from-layer="235" from-port="2" to-layer="244" to-port="0" />
<edge from-layer="235" from-port="2" to-layer="278" 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="240" to-port="0" />
<edge from-layer="238" from-port="0" to-layer="239" to-port="0" />
<edge from-layer="239" from-port="1" to-layer="240" to-port="1" />
<edge from-layer="240" from-port="2" to-layer="242" to-port="0" />
<edge from-layer="241" from-port="0" to-layer="242" to-port="1" />
<edge from-layer="242" from-port="2" to-layer="243" to-port="0" />
<edge from-layer="243" from-port="1" to-layer="244" to-port="1" />
<edge from-layer="244" from-port="2" to-layer="246" to-port="0" />
<edge from-layer="245" from-port="0" to-layer="246" to-port="1" />
<edge from-layer="246" from-port="2" to-layer="248" to-port="0" />
<edge from-layer="247" from-port="0" to-layer="248" to-port="1" />
<edge from-layer="248" from-port="2" to-layer="250" to-port="0" />
<edge from-layer="249" from-port="0" to-layer="250" to-port="1" />
<edge from-layer="250" from-port="2" to-layer="251" to-port="1" />
<edge from-layer="251" from-port="2" to-layer="288" to-port="1" />
<edge from-layer="251" from-port="2" to-layer="252" to-port="0" />
<edge from-layer="253" from-port="0" to-layer="254" to-port="0" />
<edge from-layer="254" from-port="1" to-layer="257" to-port="0" />
<edge from-layer="255" from-port="0" to-layer="256" to-port="0" />
<edge from-layer="256" from-port="1" to-layer="257" to-port="1" />
<edge from-layer="257" from-port="2" to-layer="259" to-port="0" />
<edge from-layer="258" from-port="0" to-layer="259" to-port="1" />
<edge from-layer="259" from-port="2" to-layer="260" to-port="0" />
<edge from-layer="260" from-port="1" to-layer="261" to-port="1" />
<edge from-layer="261" from-port="2" to-layer="263" to-port="0" />
<edge from-layer="262" from-port="0" to-layer="263" to-port="1" />
<edge from-layer="263" from-port="2" to-layer="265" to-port="0" />
<edge from-layer="264" from-port="0" to-layer="265" to-port="1" />
<edge from-layer="265" from-port="2" to-layer="266" to-port="1" />
<edge from-layer="266" from-port="2" to-layer="285" to-port="1" />
<edge from-layer="266" from-port="2" to-layer="267" to-port="0" />
<edge from-layer="270" from-port="0" to-layer="271" to-port="0" />
<edge from-layer="271" from-port="1" to-layer="274" to-port="0" />
<edge from-layer="272" from-port="0" to-layer="273" to-port="0" />
<edge from-layer="273" from-port="1" to-layer="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="277" to-port="0" />
<edge from-layer="277" from-port="1" to-layer="278" to-port="1" />
<edge from-layer="278" from-port="2" to-layer="280" to-port="0" />
<edge from-layer="279" from-port="0" to-layer="280" to-port="1" />
<edge from-layer="280" from-port="2" to-layer="282" to-port="0" />
<edge from-layer="281" from-port="0" to-layer="282" to-port="1" />
<edge from-layer="282" from-port="2" to-layer="284" to-port="0" />
<edge from-layer="283" from-port="0" to-layer="284" to-port="1" />
<edge from-layer="284" from-port="2" to-layer="285" to-port="0" />
<edge from-layer="285" from-port="2" to-layer="286" to-port="0" />
<edge from-layer="286" from-port="2" to-layer="287" to-port="0" />
<edge from-layer="287" from-port="1" to-layer="288" to-port="0" />
<edge from-layer="288" from-port="2" to-layer="290" to-port="0" />
<edge from-layer="289" from-port="0" to-layer="290" to-port="1" />
<edge from-layer="290" from-port="2" to-layer="292" to-port="0" />
<edge from-layer="291" from-port="0" to-layer="292" to-port="1" />
<edge from-layer="292" from-port="2" to-layer="301" to-port="0" />
<edge from-layer="293" from-port="0" to-layer="294" to-port="0" />
<edge from-layer="294" from-port="1" to-layer="297" 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="297" to-port="1" />
<edge from-layer="297" from-port="2" to-layer="299" to-port="0" />
<edge from-layer="298" from-port="0" to-layer="299" to-port="1" />
<edge from-layer="299" from-port="2" to-layer="300" to-port="0" />
<edge from-layer="300" from-port="1" to-layer="301" to-port="1" />
<edge from-layer="301" from-port="2" to-layer="303" to-port="0" />
<edge from-layer="302" from-port="0" to-layer="303" to-port="1" />
<edge from-layer="303" from-port="2" to-layer="304" to-port="1" />
<edge from-layer="304" from-port="2" to-layer="344" to-port="0" />
<edge from-layer="304" from-port="2" to-layer="306" to-port="0" />
<edge from-layer="305" from-port="0" to-layer="306" to-port="1" />
<edge from-layer="306" from-port="2" to-layer="308" to-port="0" />
<edge from-layer="307" from-port="0" to-layer="308" to-port="1" />
<edge from-layer="308" from-port="2" to-layer="310" to-port="0" />
<edge from-layer="309" from-port="0" to-layer="310" to-port="1" />
<edge from-layer="310" from-port="2" to-layer="319" to-port="0" />
<edge from-layer="311" from-port="0" to-layer="312" to-port="0" />
<edge from-layer="312" from-port="1" to-layer="315" to-port="0" />
<edge from-layer="313" from-port="0" to-layer="314" to-port="0" />
<edge from-layer="314" from-port="1" to-layer="315" to-port="1" />
<edge from-layer="315" from-port="2" to-layer="317" to-port="0" />
<edge from-layer="316" from-port="0" to-layer="317" to-port="1" />
<edge from-layer="317" from-port="2" 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="323" to-port="0" />
<edge from-layer="322" from-port="0" to-layer="323" to-port="1" />
<edge from-layer="323" from-port="2" to-layer="325" to-port="0" />
<edge from-layer="324" from-port="0" to-layer="325" to-port="1" />
<edge from-layer="325" from-port="2" to-layer="326" to-port="0" />
<edge from-layer="326" from-port="2" to-layer="327" to-port="0" />
<edge from-layer="327" from-port="1" to-layer="328" to-port="0" />
<edge from-layer="328" from-port="2" to-layer="330" to-port="0" />
<edge from-layer="329" from-port="0" to-layer="330" to-port="1" />
<edge from-layer="330" from-port="2" to-layer="332" to-port="0" />
<edge from-layer="331" from-port="0" to-layer="332" to-port="1" />
<edge from-layer="332" from-port="2" to-layer="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="344" to-port="1" />
<edge from-layer="344" from-port="2" to-layer="374" to-port="0" />
<edge from-layer="344" from-port="2" to-layer="346" to-port="0" />
<edge from-layer="345" from-port="0" to-layer="346" to-port="1" />
<edge from-layer="346" from-port="2" to-layer="348" to-port="0" />
<edge from-layer="347" from-port="0" to-layer="348" to-port="1" />
<edge from-layer="348" from-port="2" to-layer="350" to-port="0" />
<edge from-layer="349" from-port="0" to-layer="350" to-port="1" />
<edge from-layer="350" from-port="2" to-layer="359" to-port="0" />
<edge from-layer="351" from-port="0" to-layer="352" to-port="0" />
<edge from-layer="352" from-port="1" to-layer="355" to-port="0" />
<edge from-layer="353" from-port="0" to-layer="354" to-port="0" />
<edge from-layer="354" from-port="1" to-layer="355" to-port="1" />
<edge from-layer="355" from-port="2" to-layer="357" to-port="0" />
<edge from-layer="356" from-port="0" to-layer="357" to-port="1" />
<edge from-layer="357" from-port="2" to-layer="358" to-port="0" />
<edge from-layer="358" from-port="1" to-layer="359" to-port="1" />
<edge from-layer="359" from-port="2" to-layer="361" to-port="0" />
<edge from-layer="360" from-port="0" to-layer="361" to-port="1" />
<edge from-layer="361" from-port="2" to-layer="362" to-port="0" />
<edge from-layer="362" from-port="1" to-layer="371" to-port="0" />
<edge from-layer="363" from-port="0" to-layer="364" to-port="0" />
<edge from-layer="364" from-port="1" to-layer="367" to-port="0" />
<edge from-layer="365" from-port="0" to-layer="366" to-port="0" />
<edge from-layer="366" from-port="1" to-layer="367" to-port="1" />
<edge from-layer="367" from-port="2" to-layer="369" to-port="0" />
<edge from-layer="368" from-port="0" to-layer="369" to-port="1" />
<edge from-layer="369" from-port="2" to-layer="370" to-port="0" />
<edge from-layer="370" from-port="1" to-layer="371" to-port="1" />
<edge from-layer="371" from-port="2" to-layer="373" to-port="0" />
<edge from-layer="372" from-port="0" to-layer="373" to-port="1" />
<edge from-layer="373" from-port="2" to-layer="374" to-port="1" />
<edge from-layer="374" from-port="2" to-layer="376" to-port="0" />
<edge from-layer="375" from-port="0" to-layer="376" to-port="1" />
<edge from-layer="376" from-port="2" to-layer="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="381" to-port="0" />
<edge from-layer="381" from-port="2" to-layer="382" to-port="0" />
</edges>
<rt_info>
<Runtime_version value="2024.5.0-17285-ea5c1dcfdf9-releases/2024/5" />
<conversion_parameters>
<framework value="pytorch" />
<is_python_object value="True" />
</conversion_parameters>
<nncf>
<friendly_names_were_updated value="True" />
<weight_compression>
<advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
<all_layers value="False" />
<awq value="False" />
<backup_mode value="int8_asym" />
<gptq value="False" />
<group_size value="-1" />
<ignored_scope value="[]" />
<lora_correction value="False" />
<mode value="int8_asym" />
<ratio value="1" />
<scale_estimation value="False" />
<sensitivity_metric value="weight_quantization_error" />
</weight_compression>
</nncf>
<optimum>
<optimum_intel_version value="1.21.0.dev0+d357376" />
<optimum_version value="1.23.3" />
<pytorch_version value="2.5.1" />
<transformers_version value="4.46.3" />
</optimum>
</rt_info>
</net>