MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts

State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pióro, Maciej, Ciebiera, Kamil, Król, Krystian, Ludziejewski, Jan, Krutul, Michał, Krajewski, Jakub, Antoniak, Szymon, Miłoś, Piotr, Cygan, Marek, Jaszczur, Sebastian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We propose that to unlock the potential of SSMs for scaling, they should be combined with MoE. We showcase this on Mamba, a recent SSM-based model that achieves remarkable performance. Our model, MoE-Mamba, outperforms both Mamba and baseline Transformer-MoE. In particular, MoE-Mamba reaches the same performance as Mamba in $2.35\times$ fewer training steps while preserving the inference performance gains of Mamba against Transformer.
DOI:10.48550/arxiv.2401.04081