|
|
@@ -41,7 +41,7 @@ def load_quantized_LLaMA(model_name):
|
|
|
print(f"Could not find {pt_model}, exiting...")
|
|
|
exit()
|
|
|
|
|
|
- model = load_quant(path_to_model, str(pt_path), bits)
|
|
|
+ model = load_quant(path_to_model, os.path.abspath(pt_path), bits)
|
|
|
|
|
|
# Multi-GPU setup
|
|
|
if shared.args.gpu_memory:
|