|
|
<?xml version="1.0"?> |
|
|
<net name="Model199" version="11"> |
|
|
<layers> |
|
|
<layer id="0" name="input" type="Parameter" version="opset1"> |
|
|
<data shape="?,?" element_type="i64" /> |
|
|
<output> |
|
|
<port id="0" precision="I64" names="input"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="1" name="self.weight" type="Const" version="opset1"> |
|
|
<data element_type="u8" shape="49280, 960" offset="0" size="47308800" /> |
|
|
<output> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="2" name="Convert_834939" type="Convert" version="opset1"> |
|
|
<data destination_type="f16" /> |
|
|
<input> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="3" name="self.weight/zero_point" type="Const" version="opset1"> |
|
|
<data element_type="u8" shape="49280, 1" offset="47308800" size="49280" /> |
|
|
<output> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>49280</dim> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="4" name="Convert_834942" type="Convert" version="opset1"> |
|
|
<data destination_type="f16" /> |
|
|
<input> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>49280</dim> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="5" name="self.weight/zero_point/subtract" type="Subtract" version="opset1"> |
|
|
<data auto_broadcast="numpy" /> |
|
|
<input> |
|
|
<port id="0" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="6" name="self.weight/scale" type="Const" version="opset1"> |
|
|
<data element_type="f16" shape="49280, 1" offset="47358080" size="98560" /> |
|
|
<output> |
|
|
<port id="0" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="7" name="self.weight/fq_weights_0" type="Multiply" version="opset1"> |
|
|
<data auto_broadcast="numpy" /> |
|
|
<input> |
|
|
<port id="0" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="8" name="self.weight/fq_weights_0/convert" type="Convert" version="opset1"> |
|
|
<data destination_type="f32" /> |
|
|
<input> |
|
|
<port id="0" precision="FP16"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="9" name="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="10" name="aten::embedding/Constant" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="" offset="47456640" size="4" /> |
|
|
<output> |
|
|
<port id="0" precision="I32" /> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="11" name="aten::embedding/Gather" type="Gather" version="opset8"> |
|
|
<data batch_dims="0" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>49280</dim> |
|
|
<dim>960</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="inputs_embeds"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="12" name="Result_526194" type="Result" version="opset1" output_names="inputs_embeds"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>960</dim> |
|
|
</port> |
|
|
</input> |
|
|
</layer> |
|
|
</layers> |
|
|
<edges> |
|
|
<edge from-layer="0" from-port="0" to-layer="9" 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="0" to-layer="4" to-port="0" /> |
|
|
<edge from-layer="4" from-port="1" to-layer="5" to-port="1" /> |
|
|
<edge from-layer="5" from-port="2" to-layer="7" to-port="0" /> |
|
|
<edge from-layer="6" from-port="0" to-layer="7" to-port="1" /> |
|
|
<edge from-layer="7" from-port="2" to-layer="8" to-port="0" /> |
|
|
<edge from-layer="8" from-port="1" to-layer="11" to-port="0" /> |
|
|
<edge from-layer="9" from-port="1" to-layer="11" to-port="1" /> |
|
|
<edge from-layer="10" from-port="0" to-layer="11" to-port="2" /> |
|
|
<edge from-layer="11" from-port="3" to-layer="12" 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> |
|
|
<nncf> |
|
|
<friendly_names_were_updated value="True" /> |
|
|
<version value="2.17.0" /> |
|
|
<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, '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}, 'lora_adapter_rank': 256, 'backend_params': {}}" /> |
|
|
<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_asym" /> |
|
|
<ratio value="1.0" /> |
|
|
<scale_estimation value="False" /> |
|
|
<sensitivity_metric value="weight_quantization_error" /> |
|
|
</weight_compression> |
|
|
</nncf> |
|
|
<optimum> |
|
|
<nncf_version value="2.17.0" /> |
|
|
<optimum_intel_version value="1.24.0" /> |
|
|
<optimum_version value="1.26.1" /> |
|
|
<pytorch_version value="2.7.1" /> |
|
|
<transformers_version value="4.52.4" /> |
|
|
</optimum> |
|
|
</rt_info> |
|
|
</net> |
|
|
|
