disable reload

Signed-off-by: yiliu30 <yi4.liu@intel.com>

Author: yiliu30

examples/pytorch/nlp/huggingface_models/language-modeling/quantization/auto_round/deepseek/quantize.py

@@ -68,6 +68,7 @@ def quant_model(args):
         fp_layers=config["fp_layers"],
         export_format=export_format,
         output_dir=output_dir,
+        reloading=False,
     )
 
     # quantizer execute

examples/pytorch/nlp/huggingface_models/language-modeling/quantization/auto_round/qwen/quantize.py

@@ -69,6 +69,7 @@ def quant_model(args):
         disable_opt_rtn=True,
         low_gpu_mem_usage=True,
         output_dir=output_dir,
+        reloading=False,
     )
 
     # quantizer execute