| <?xml version="1.0"?>
|
| <net name="Model3" version="11">
|
| <layers>
|
| <layer id="0" name="hidden_states" type="Parameter" version="opset1">
|
| <data shape="?,?" element_type="f32" />
|
| <output>
|
| <port id="0" precision="FP32" names="hidden_states">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="1" name="Constant_113664" type="Const" version="opset1">
|
| <data element_type="i64" shape="5" offset="0" size="40" />
|
| <output>
|
| <port id="0" precision="I64" names="8">
|
| <dim>5</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="2" name="aten::view/Reshape" type="Reshape" version="opset1">
|
| <data special_zero="false" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>-1</dim>
|
| </port>
|
| <port id="1" precision="I64">
|
| <dim>5</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="14,9,hidden_states_1,input">
|
| <dim>-1</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="3" name="self.proj.weight" type="Const" version="opset1">
|
| <data element_type="i8" shape="1280, 3, 2, 14, 14" offset="40" size="1505280" />
|
| <output>
|
| <port id="0" precision="I8">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="4" name="Convert_1354782" type="Convert" version="opset1">
|
| <data destination_type="f16" />
|
| <input>
|
| <port id="0" precision="I8">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP16">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="5" name="self.proj.weight/scale" type="Const" version="opset1">
|
| <data element_type="f16" shape="1280, 1, 1, 1, 1" offset="1505320" size="2560" />
|
| <output>
|
| <port id="0" precision="FP16">
|
| <dim>1280</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="6" name="self.proj.weight/fq_weights_1" type="Multiply" version="opset1">
|
| <data auto_broadcast="numpy" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| <port id="1" precision="FP16">
|
| <dim>1280</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP16">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="7" name="self.proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
|
| <data destination_type="f32" />
|
| <input>
|
| <port id="0" precision="FP16">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="1" precision="FP32">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="8" name="__module.proj/aten::_convolution/Convolution" type="Convolution" version="opset1">
|
| <data strides="2, 14, 14" dilations="1, 1, 1" pads_begin="0, 0, 0" pads_end="0, 0, 0" auto_pad="explicit" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| <port id="1" precision="FP32">
|
| <dim>1280</dim>
|
| <dim>3</dim>
|
| <dim>2</dim>
|
| <dim>14</dim>
|
| <dim>14</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="33">
|
| <dim>-1</dim>
|
| <dim>1280</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="9" name="Constant_113711" type="Const" version="opset1">
|
| <data element_type="i64" shape="2" offset="1507880" size="16" />
|
| <output>
|
| <port id="0" precision="I64" names="18">
|
| <dim>2</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="10" name="aten::view/Reshape_1" type="Reshape" version="opset1">
|
| <data special_zero="false" />
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1280</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| <dim>1</dim>
|
| </port>
|
| <port id="1" precision="I64">
|
| <dim>2</dim>
|
| </port>
|
| </input>
|
| <output>
|
| <port id="2" precision="FP32" names="last_hidden_state">
|
| <dim>-1</dim>
|
| <dim>1280</dim>
|
| </port>
|
| </output>
|
| </layer>
|
| <layer id="11" name="Result_113738" type="Result" version="opset1" output_names="last_hidden_state">
|
| <input>
|
| <port id="0" precision="FP32">
|
| <dim>-1</dim>
|
| <dim>1280</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="2" to-port="1" />
|
| <edge from-layer="2" from-port="2" to-layer="8" to-port="0" />
|
| <edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
|
| <edge from-layer="4" from-port="1" to-layer="6" to-port="0" />
|
| <edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
|
| <edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
|
| <edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
|
| <edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
|
| <edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
|
| <edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
|
| </edges>
|
| <rt_info>
|
| <Runtime_version value="2025.3.0-19807-44526285f24-releases/2025/3" />
|
| <conversion_parameters>
|
| <framework value="pytorch" />
|
| <is_python_object value="True" />
|
| </conversion_parameters>
|
| <nncf>
|
| <friendly_names_were_updated value="True" />
|
| <version value="2.18.0" />
|
| <weight_compression>
|
| <advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'ignore', 'min_adjusted_group_size': 16, '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}" />
|
| <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="2.18.0" />
|
| <optimum_intel_version value="1.26.0.dev0+bc13ae5" />
|
| <optimum_version value="1.27.0" />
|
| <pytorch_version value="2.7.1" />
|
| <transformers_version value="4.51.3" />
|
| </optimum>
|
| </rt_info>
|
| </net>
|
|
|
