Instructions to use nmcco/15_flashattn_gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nmcco/15_flashattn_gemma with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nmcco/15_flashattn_gemma", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 266c84a4b4d238c380a18cae29eb7d4944fd6da2a5debc4f7b3992452468b574
- Size of remote file:
- 6.84 kB
- SHA256:
- d451443f35711e53bb414237b73fa84f849b49520b49e2a8c7e97e4d8ba6b5c1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.