Instructions to use CRD716/ggml-vicuna-1.1-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use CRD716/ggml-vicuna-1.1-quantized with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("undefined") model.load_adapter("CRD716/ggml-vicuna-1.1-quantized", set_active=True) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 3815a3cc8cc6253a0c83fb8ba48bfbfc2b7b4302917caa53b782800a8a933004
- Size of remote file:
- 7.32 GB
- SHA256:
- e8c1ff6b8d3545838213da84aa2e2d2fc2ca2276a69c7cca7b5859393da83299
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.