Instructions to use Zyphra/Mamba-370M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Zyphra/Mamba-370M with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Zyphra/Mamba-370M", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Error Loading The Model
#3
by jonathanjordan21 - opened
Code :
from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel
model = MambaLMHeadModel.from_pretrained("Zyphra/Mamba-370M", device="cuda")
Error Statement :
RuntimeError: Error(s) in loading state_dict for MambaLMHeadModel:
Unexpected key(s) in state_dict: "backbone.norm_f.bias".
This sounds like a configuration issue. Please, take a look at this: https://huggingface.co/Zyphra/Mamba-370M/discussions/2