Instructions to use FasterDecoding/medusa-vicuna-33b-v1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FasterDecoding/medusa-vicuna-33b-v1.3 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FasterDecoding/medusa-vicuna-33b-v1.3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
File size: 144 Bytes
a03af72 | 1 2 3 4 5 6 7 | {
"base_model_name_or_path": "lmsys/vicuna-33b-v1.3",
"medusa_num_heads": 2,
"medusa_num_layers": 1,
"transformers_version": "4.31.0"
}
|