---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
language:
- en
---
Model of the paper [MoM: Linear Sequence Modeling with Mixture-of-Memories](https://arxiv.org/abs/2502.13685).

The model was trained on a sample of SlimPajama with 100B tokens. We use Gated-Deltanet as the memory update mechanism.