Instructions to use cackerman/rewrites_llama13bchat_4bit_ft_full3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cackerman/rewrites_llama13bchat_4bit_ft_full3 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cackerman/rewrites_llama13bchat_4bit_ft_full3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K