junnei

/

gemma-3-4b-it-speech

like 29

i am facing the issue when running inference on the latest version of transformers, peft and accelerate.

During handling of the above exception, another exception occurred:

AttributeError                            Traceback (most recent call last)

/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py in __getattr__(self, name)
   1926             if name in modules:
   1927                 return modules[name]
-> 1928         raise AttributeError(
   1929             f"'{type(self).__name__}' object has no attribute '{name}'"
   1930         )

AttributeError: 'Gemma3TextModel' object has no attribute 'prepare_inputs_for_generation'