Instructions to use jsm40/gemma-4-31B-it-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jsm40/gemma-4-31B-it-assistant with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jsm40/gemma-4-31B-it-assistant") model = AutoModelForCausalLM.from_pretrained("jsm40/gemma-4-31B-it-assistant", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 510431bc395e065ff83be0ca87cd667a93c26095f8bd24a1a22fe529fa8585b1
- Size of remote file:
- 939 MB
- SHA256:
- 9f80df6099fa1fd7db71220ec9ee864d5ecff769878697dd5763e4285b15a1da
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.