Transformers
English
quantization
quantization-aware-training
bcjr
trellis-coded-quantization
llama
2-bit
Instructions to use Venugopalan2610/BCJR-QAT-Llama-3.2-1B-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Venugopalan2610/BCJR-QAT-Llama-3.2-1B-2bit with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Venugopalan2610/BCJR-QAT-Llama-3.2-1B-2bit", dtype="auto") - Notebooks
- Google Colab
- Kaggle