Instructions to use FasterDecoding/medusa-vicuna-13b-v1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FasterDecoding/medusa-vicuna-13b-v1.3 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FasterDecoding/medusa-vicuna-13b-v1.3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model_name_or_path": "lmsys/vicuna-13b-v1.3", | |
| "medusa_num_heads": 2, | |
| "medusa_num_layers": 1, | |
| "transformers_version": "4.31.0" | |
| } | |