text_proj.xml

<?xml version="1.0"?>
<net name="Model0" version="11">
	<layers>
		<layer id="0" name="input" type="Parameter" version="opset1">
			<data shape="?,?" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="input">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="self.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="256, 768" offset="0" size="393216" />
			<output>
				<port id="0" precision="FP16" names="self.weight">
					<dim>256</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="self.weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>256</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>256</dim>
					<dim>768</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="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>
				</port>
				<port id="1" precision="FP32">
					<dim>256</dim>
					<dim>768</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>256</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Constant_1906_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 256" offset="393216" size="512" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>256</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="Constant_1906" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>256</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>256</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="aten::linear/Add" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>256</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>256</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>-1</dim>
					<dim>256</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="Result_9" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>256</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
		<edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
		<edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
		<edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
		<edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
	</rt_info>
</net>