thinker_embeddings_model.xml

<?xml version="1.0"?>
<net name="Model3" version="11">
	<layers>
		<layer id="0" name="input_ids" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="input_ids">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="self.embed_tokens.weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="151936, 2048" offset="0" size="622329856" />
			<output>
				<port id="0" precision="FP16" names="self.embed_tokens.weight">
					<dim>151936</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="self.embed_tokens.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>151936</dim>
					<dim>2048</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>151936</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="__module.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="4" name="__module.embed_tokens/aten::embedding/Constant" type="Const" version="opset1">
			<data element_type="i32" shape="" offset="622329856" size="4" />
			<output>
				<port id="0" precision="I32" />
			</output>
		</layer>
		<layer id="5" name="__module.embed_tokens/aten::embedding/Gather" type="Gather" version="opset8">
			<data batch_dims="0" />
			<input>
				<port id="0" precision="FP32">
					<dim>151936</dim>
					<dim>2048</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">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="Result_25620" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>2048</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="5" to-port="0" />
		<edge from-layer="3" from-port="1" to-layer="5" to-port="1" />
		<edge from-layer="4" from-port="0" to-layer="5" to-port="2" />
		<edge from-layer="5" from-port="3" to-layer="6" to-port="0" />
	</edges>
	<rt_info>
		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
	</rt_info>
</net>