Instructions to use mindw96/KULLM3_bnb_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mindw96/KULLM3_bnb_4bit with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mindw96/KULLM3_bnb_4bit", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 6cad243a6424ac14d34b46da1b01ddb4bfc830d3b03b599e689b66c012d33c22
- Size of remote file:
- 1.3 GB
- SHA256:
- f82eefd4367b2e3681db98c4bb7e7e3f70902ef4476fe325999031d20c92373b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.