wiola

Wiola: a novel decoder-only Small Language Model with Spiral Rotary Positional Encoding, Gated Cross-Layer Attention, Adaptive Token Merging, Dual-Stream Feed-Forward, and WiolaRMSNorm.


Keywords
small-language-model, transformer, language-model, spiral-rotary, attention, pytorch, huggingface
License
Apache-2.0
Install
pip install wiola==0.1.1