Instructions to use havenhq/mamba-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use havenhq/mamba-chat with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("havenhq/mamba-chat", dtype="auto") - Notebooks
- Google Colab
- Kaggle
performance thoughts
#4
by RonanMcGovern - opened
Thanks for making this model.
It's interesting how it seems weaker than Phi-2 - at least on coding. I notice there is an OpenHermes fine-tune too and it has the same issue (e.g. fails to write a function to add up the first N fibonacci numbers).
Any thoughts on why this might be the case?