openvino_text_embeddings_per_layer_model.xml

<?xml version="1.0"?>
<net name="Model9" 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="aten::zeros/Convert" type="Const" version="opset1">
			<data element_type="f32" shape="" offset="0" size="4" />
			<output>
				<port id="0" precision="FP32" />
			</output>
		</layer>
		<layer id="2" name="aten::size/ShapeOf" type="ShapeOf" version="opset3">
			<data output_type="i64" />
			<input>
				<port id="0" precision="I64">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="I64">
					<dim>2</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="Constant_312973" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="4" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Constant_312974" type="Const" version="opset1">
			<data element_type="i64" shape="1" offset="12" size="8" />
			<output>
				<port id="0" precision="I64">
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="prim::ListConstruct/SequenceMark" type="Concat" version="opset1">
			<data axis="0" />
			<input>
				<port id="0" precision="I64">
					<dim>2</dim>
				</port>
				<port id="1" precision="I64">
					<dim>1</dim>
				</port>
				<port id="2" precision="I64">
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="3" precision="I64">
					<dim>4</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="aten::zeros/Broadcast" type="Broadcast" version="opset3">
			<data mode="numpy" />
			<input>
				<port id="0" precision="FP32" />
				<port id="1" precision="I64">
					<dim>4</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="text_embeds_per_layer">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>30</dim>
					<dim>0</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="Result_313021" type="Result" version="opset1" output_names="text_embeds_per_layer">
			<input>
				<port id="0" precision="FP32">
					<dim>-1</dim>
					<dim>-1</dim>
					<dim>30</dim>
					<dim>0</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="6" to-port="0" />
		<edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
		<edge from-layer="3" from-port="0" 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="1" />
		<edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
	</edges>
	<rt_info>
		<info name="OpenVINO Runtime" value="2026.3.1-22476-759c5a6ab8c-releases/2026/3" />
		<Runtime_version value="2026.3.1-22476-759c5a6ab8c-releases/2026/3" />
		<conversion_parameters>
			<framework value="pytorch" />
			<is_python_object value="True" />
		</conversion_parameters>
		<nncf>
			<friendly_names_were_updated value="True" />
			<version value="3.3.0" />
			<weight_compression>
				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None, 'adaptive_codebook_params': {'value_type': 'f8e4m3', 'across_blocks': False, 'num_elements': 16}}" />
				<all_layers value="False" />
				<awq value="False" />
				<backup_mode value="int8_asym" />
				<compression_format value="dequantize" />
				<gptq value="False" />
				<group_size value="-1" />
				<ignored_scope value="[]" />
				<lora_correction value="False" />
				<mode value="int8_sym" />
				<ratio value="1.0" />
				<scale_estimation value="False" />
				<sensitivity_metric value="weight_quantization_error" />
			</weight_compression>
		</nncf>
		<optimum>
			<nncf_version value="3.3.0" />
			<optimum_intel_version value="2.2.0.dev0+dd4ed1a" />
			<optimum_version value="2.3.0" />
			<pytorch_version value="2.11.0+cu128" />
			<transformers_version value="5.5.0" />
		</optimum>
	</rt_info>
</net>