Does the quantization script (convert_hf.py) work on finetuned models.

[Ramnathan-zoimeet]

While running the script on fine tuned models am getting the following error.

"The state dictionary of the model you are training to load is corrupted" ValueError: The state dictionary of the model you are training to load is corrupted. Are you sure it was properly saved?"

Also is there any other way to make it work for finetuned model's?