license: apache-2.0
language:
- en
StripedHyena-Nous-7B (SH-N 7B)
About
One of the focus areas at Together Research is new architectures for long context, improved training, and inference performance over the Transformer architecture. Spinning out of a research program from our team and academic collaborators, with roots in signal processing-inspired sequence models, we are excited to introduce the StripedHyena models. StripedHyena is the first alternative model competitive with the best open-source Transformers of similar sizes in short and long-context evaluations.
StripedHyena-Nous-7B (SH-N 7B) is our chat model for this release, and was developed with our collaborators at Nous Research.
- Read more here in our blog.
- Play with the model on our playground!
- Dive into the details of our standalone implementation, and our related research: 1, 2, 3.
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.
- Low latency, faster decoding and higher throughput than Transformers.
- Improvement to training and inference-optimal scaling laws, compared to optimized Transformer architectures such as Llama-2.
- Trained on sequences of up to 32k, allowing it to process longer prompts.