Instructions to use Varosa/llama-model-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Varosa/llama-model-quantized with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Varosa/llama-model-quantized", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 29 Bytes
1c73c5c | 1 2 3 | {
"model_type": "llama"
} |