Create new configuration


* - required field

Model

Select model model
input * {{ input === 'custom' ? '(Add your custom input node)' : input }} {{ inputs.length > 1 && order['input'].indexOf(input) !== -1 && input !== 'custom' ? '(' + (order['input'].indexOf(input) + 1) + ')' : null }} input * output * {{ output === 'custom' ? '(Add your custom output node)' : output }} {{ outputs.length > 1 && order['output'].indexOf(output) !== -1 && output !== 'custom' ? '(' + (order['output'].indexOf(output) + 1) + ')' : null }} output * output *
Order of the inputs and outputs matters.

Select precision

Precision

{{ precision.name }}

Run tuning




Set configuration

Model domain

model domain NLP {{ domain.name | modelList | titlecase }}

Evaluation

evaluation dataset {{ dataLoader.name === 'custom' ? '(Add your custom data loader)' : dataLoader.name }} {{ param.name }} dataset location * Use the same data as calibration
Fill the code template before tuning calibration dataset {{ dataLoader.name === 'custom' ? '(Add your custom data loader)' : dataLoader.name }} {{ param.name }} dataset location * Fill the code template before tuning
calibration sampling size

Transforms

transform {{ index }} {{ transformation.name === 'custom' ? '(Add your custom transformation)' : transformation.name }} {{ param.name }}

Metric

metric {{ metric.name === 'custom' ? '(Add your custom metric)' : metric.name }} Fill the code template before tuning {{ param.name }} {{ option }} {{ param.name }} yes no {{ param.name }}

Show advanced parameters

Tune

tuning strategy {{ tuning.name }} accuracy goal objective {{ objective.name }}
timeout max trials random seed

Quantization

approach {{ approach.name }}

Benchmarking

batch size warmup iteration cores per instance number of instances cores_per_instance * num_of_instance should not be greater than cores_per_socket ({{ secondFormGroup.get('num_of_instance').value }} * {{ secondFormGroup.get('cores_per_instance').value }} > {{ modelService.systemInfo['cores_per_socket'] }})