Search Results for author:
Found 1 papers, 1 papers with code
Scalable MatMul-free Language Modeling
Our experiments show that our proposed MatMul-free models achieve performance on-par with state-of-the-art Transformers that require far more memory during inference at a scale up to at least 2. 7B parameters.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
