Offline Flow : Conversion (WIP)¶
Convert the Base Model¶
Same Converter/Quantizer for LoRA and non-LoRA usages
Converter has a new “–lora_weight_list” parameter to pass LoRA Weights Names, to identify as “updatable tensors” in the graph
Import the LoRA Adapters via. qairt-lora-importer¶
Note: This feature is currently supported only for ONNX models
What is the format of “LoRA Weights Names” provided to qairt-converter tool with –lora_weight_list option?
A text file contains LoRA adapter weight tensor names with newline as delimiter
Refer to the below sample code that generates a text file with LoRA adapter weight tensor names from LoRA adapter .safetensors file
from safetensors.numpy import load_file
def save_tensor_names(safetensor_path, save_path="./tensor_names.txt"):
tensor_name_to_data_map = load_file(safetensor_path)
with open(save_path, 'w') as text_file:
for tensorAtt_name in tensor_name_to_data_map:
text_file.write(tensor_name + '\n')