Issue loading google/gemma-4-E2B-it with AutoProcessor (Unrecognized processing class)
I’m trying to load the model google/gemma-4-E2B-it using the Hugging Face Transformers library, but I’m encountering an issue when initializing the processor. Any help would be appreciated. Thanks in advance.
Traceback (most recent call last):
File "/path/to/project/gemma4_generate.py", line 72, in
processor = AutoProcessor.from_pretrained(MODEL_NAME)
File "/path/to/env/lib/python3.9/site-packages/transformers/models/auto/processing_auto.py", line 424, in from_pretrained
raise ValueError(
ValueError: Unrecognized processing class in google/gemma-4-E2B-it. Can't instantiate a processor, a tokenizer, an image processor or a feature extractor for this model. Make sure the repository contains the files of at least one of those processing classes.
Environment
- Python: 3.9
- Transformers: (latest installed via pip install -U transformers accelerate torch)
Hi @dipakmeher51
Could you please confirm the version of the transformers you are using? It works as expected in version 5.5.0.
Thanks
Hi,
The transformer version I am using is 4.57.6. That could the reason since you mentioned it works as expected in version 5.5.0. Let me try.
Thanks.