Instructions to use codingninja/gemma-32k-pa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codingninja/gemma-32k-pa with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("codingninja/gemma-32k-pa", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Only use small subset for testing... otherwise using insane amount of RAM.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support