Instructions to use google/gemma-4-12B-it-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B-it-assistant with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-12B-it-assistant") model = AutoModelForCausalLM.from_pretrained("google/gemma-4-12B-it-assistant", device_map="auto") - Notebooks
- Google Colab
- Kaggle
running error with transformers
#3
by yxnchen - opened
when running the model with the newest transformers framework, there is an error:
ModuleNotFoundError: Could not import module 'Gemma4UnifiedProcessor'. Are this object's requirements defined correctly?
Hi @yxnchen , thank you for reporting this. We tested the google/gemma-4-12B-it-assistant model notebook with the latest transformers version 5.10.2 using pip install -U transformers and code ran successfully without any errors. Please refer to the gist.
Could you help us debug further by sharing the following:
- Your exact transformer version, how exactly you installed transformers?
- Was it
pip install -U transformersor any specific version - Full error traceback.