Instructions to use state-spaces/mamba-370m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use state-spaces/mamba-370m with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("state-spaces/mamba-370m", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Adds tags for discoverability and code snippets
#3
by Wauplin HF Staff - opened
This PR is related to https://github.com/state-spaces/mamba/pull/471 and https://github.com/huggingface/huggingface.js/pull/802.
The goal is to improve discoverability and usability of mamba models by adding tags to the modelcard metadata.
Once PRs are merged, users will see a code snippet in Use this model to load the model using samba_ssm:
from mamba_ssm import MambaLMHeadModel
model = MambaLMHeadModel.from_pretrained("state-spaces/mamba-370m")
This PR is ready for review.