Skip to content


A base class for all of Deci's model classes. A model stores data in constant fields, and let us manipulate the data in a more readable way.


Name Type Description Notes
update_time datetime [optional]
creation_time datetime [optional]
id str [optional]
deleted bool [optional] [default to False]
model_id str
name str
benchmark dict(str, list[object]) [optional]
primary_hardware HardwareReturnSchema
primary_batch_size int [optional] [default to 1]
accuracy_metrics list[AccuracyMetric] [optional] [default to []]
dl_task DeepLearningTask
quantization_level QuantizationLevel
architecture_family str
model_size float [optional] [default to 0]
optimization_state ModelOptimizationState
version str
optimization_start_date datetime [optional]
benchmark_start_date datetime [optional]
owner BaseUserMetadata
downloads_count int
dataset_name DatasetName
framework FrameworkType
input_dimensions list[object]
dl_task_label DeepLearningTaskLabel

[Back to Model list] [Back to API list] [Back to README]