Method ApplyLoraAdapter
ApplyLoraAdapter(string, float, int)
Applies a Low-Rank Adaptation (LoRA) transformation to the model weights using parameters from a specified file. This method adjusts the model weights dynamically based on the adaptation parameters provided in the file.
public void ApplyLoraAdapter(string path, float scale = 1, int threadCount = -1)
Parameters
path
stringThe path to the LoRA adapter source file. This parameter must not be null or empty.
scale
floatThe scale factor for the LoRA adapter source. This must be a positive value. The default value is 1.
threadCount
intThe number of threads to allocate for the operation. If this value is less than or equal to 0, the ThreadCount will be used.
Exceptions
- ArgumentNullException
Thrown if the
path
parameter is null or empty.- ArgumentOutOfRangeException
Thrown if the
scale
parameter is less than or equal to 0.- FileNotFoundException
Thrown if the file specified by the
path
parameter does not exist.- InvalidDataException
Thrown if the file header is invalid.
- RuntimeException
Thrown if the LoRA adaptation fails to load or apply correctly from the specified file. This may occur due to issues such as reading the file, parsing the adaptation parameters, or applying these parameters to the model.
ApplyLoraAdapter(LoraAdapterSource, int)
Applies a Low-Rank Adaptation (LoRA) transformation to the model weights using parameters from a LoraAdapterSource instance. This method adjusts the model weights dynamically based on the adaptation parameters provided in the LoraAdapterSource.
public void ApplyLoraAdapter(LoraAdapterSource loraAdapterSource, int threadCount = -1)
Parameters
loraAdapterSource
LoraAdapterSourceAn instance of LoraAdapterSource containing the path to the LoRA parameters and the scale factor.
threadCount
intThe number of threads to allocate for the operation. If this value is less than or equal to 0, the ThreadCount will be used.
Exceptions
- ArgumentNullException
Thrown if the
loraAdapterSource
parameter is null.- RuntimeException
Thrown if the LoRA adaptation fails to load or apply correctly from the specified file. This may occur due to issues such as reading the file, parsing the adaptation parameters, or applying these parameters to the model.