Instructions to use aspctu/llama31-70b-engine-4gpu-basic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aspctu/llama31-70b-engine-4gpu-basic with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("aspctu/llama31-70b-engine-4gpu-basic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 48653f791c7f3816fde3dfe683a75cc1dca0e7eca8c3c21ccd13e07a616b372d
- Size of remote file:
- 37 GB
- SHA256:
- 7050dfe072c0d05032b1d053e2e9f812713797916827d2d2f47934061477a62e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.