BlackMamba
![](https://cdn-uploads.huggingface.co/production/uploads/65bc13717c6ad1994b6619e9/JdxNtwFrmEAnjJ0_MP5A3.jpeg)
BlackMamba: Mixture of Experts for State-space models
Quentin Anthony*, Yury Tokpanov*, Paolo Glorioso*, Beren Millidge*
Paper: https://arxiv.org/abs/2402.01771
![](https://cdn-uploads.huggingface.co/production/uploads/65bc13717c6ad1994b6619e9/aHpEc5tnCJShO2Kn0f637.png)
About
We provide inference code for our BlackMamba model in our github repository: https://github.com/Zyphra/BlackMamba
BlackMamba is an novel architecture which combines state-space models (SSMs) with mixture of experts (MoE). It uses Mamba as its SSM block and switch transformer as its MoE block base. BlackMamba is extremely low latency for generation and inference, providing significant speedups over all of classical transformers, MoEs, and Mamba SSM models. Additionally, due to its SSM sequence mixer, BlackMamba retains linear compuational complexity in the sequence length.
- Downloads last month
- 22