Transformers
PyTorch
Inference Endpoints
BlackMamba-2.8B / README.md
yury-zyphra's picture
Update README.md
1f55876 verified
|
raw
history blame
602 Bytes
metadata
license: apache-2.0

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.