llama_apply_lora_from_file method
Apply a LoRA adapter to a loaded model path_base_model is the path to a higher quality model to use as a base for the layers modified by the adapter. Can be NULL to use the current loaded model. The model needs to be reloaded before applying a new adapter, otherwise the adapter will be applied on top of the previous one Returns 0 on success
Implementation
int llama_apply_lora_from_file(
ffi.Pointer<llama_context> ctx,
ffi.Pointer<ffi.Char> path_lora,
double scale,
ffi.Pointer<ffi.Char> path_base_model,
int n_threads,
) {
return _llama_apply_lora_from_file(
ctx,
path_lora,
scale,
path_base_model,
n_threads,
);
}