Pretrained Hybrids with MAD Skills

While Transformers underpin modern large language models (LMs), there is a growing list of alternative architectures with new capabilities, promises, and tradeoffs. This makes choosing the right LM architecture challenging. Recently-proposed hybrid architectures seek a best-of-all-worlds approach that reaps the benefits of all architectures. Hybrid design is difficult for two reasons: it requires manual expert-driven search, and new hybrids must be trained from scratch. We propose Manticore, a framework that addresses these challenges. Manticore automates the design of hybrid architectures while reusing pretrained models to create pretrained hybrids. Our approach augments ideas from differentiable Neural Architecture Search (NAS) by incorporating simple projectors that translate features between pretrained blocks from different architectures. We then fine-tune hybrids that combine pretrained models with different architectures---such as GPT and Mamba---end-to-end. With Manticore, we enable LM selection without training multiple models, the construction of pretrained hybrids from existing pretrained models, and the ability to program hybrids to have certain capabilities. Manticore hybrids outperform existing hybrids, achieve strong performance on Long Range Arena (LRA), and can improve on pretrained transformers and state space models.