metadata
license: apache-2.0
language:
- en
StripedHyena-Hessian-7B (SH-7B)
Model Architecture
StripedHyena is a hybrid architecture composed of multi-head, grouped-query attention and gated convolutions arranged in Hyena blocks, different from traditional decoder-only Transformers.
- Costant memory decoding in Hyena blocks via representation of convolutions as state-space models (modal or canonical form), or as truncated filters.
- Lower latency to preprocess long prompts.
- Improvements to training and inference compute-optimal scaling laws, compared to Transformers.