Instructions to use google/gemma-4-E4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-E4B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/gemma-4-E4B") model = AutoModelForImageTextToText.from_pretrained("google/gemma-4-E4B") - Notebooks
- Google Colab
- Kaggle
Chat template to make vLLM deployment working?
1
#4 opened 8 days ago
by
vrdn23
Missing FIM Tokens?
3
#3 opened about 1 month ago
by
dervagabund