Instructions to use codesage/codesage-small-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codesage/codesage-small-v2 with Transformers:
# Load model directly from transformers import CodeSage model = CodeSage.from_pretrained("codesage/codesage-small-v2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Allow for attention weights to be extracted.
#2
by FJFehr - opened
There is a small bug in indexing which didn't allow me to get the attentions out. I think this change fixes it.