MoM
Collection
9 items
•
Updated
•
2
Model of the paper MoM: Linear Sequence Modeling with Mixture-of-Memories.
The model was trained on a sample of SlimPajama with 15B tokens. We use Gated-Deltanet as the memory update mechanism.
- Downloads last month
- 21
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.