Instructions to use DoNotChoke/output_fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DoNotChoke/output_fp16 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DoNotChoke/output_fp16", dtype="auto") - Notebooks
- Google Colab
- Kaggle