Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Lists
Only you see this
Abstract
The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models demands significantly larger datasets and computational resources compared to text-only LLMs. To address the scaling challenges, we introduce Mixture-of-Transformers (MoT), a sparse multi-modal transformer architecture that significantly reduces pretraining computational costs. MoT decouples non-embedding parameters of the model by modality -- including feed-forward networks, attention matrices, and layer normalization -- enabling modality-specific processing with global self-attention over the full input sequence. We evaluate MoT across multiple settings and model scales. In the Chameleon 7B setting (autoregressive text-and-image generation), MoT matches the dense baseline's performance using only 55.8% of the FLOPs. When extended to include speech, MoT reaches speech performance comparable to the dense baseline with only 37.2% of the FLOPs. In the Transfusion setting, where text and image are trained with different objectives, a 7B MoT model matches the image modality performance of the dense baseline with one third of the FLOPs, and a 760M MoT model outperforms a 1.4B dense baseline across key image generation metrics. System profiling further highlights MoT's practical benefits, achieving dense baseline image quality in 47.2% of the wall-clock time and text quality in 75.6% of the wall-clock time (measured on AWS p4de.24xlarge instances with NVIDIA A100 GPUs).
BibTeX
@article{liang2024mixture,
author = {Weixin Liang and LILI YU and Liang Luo and Srini Iyer and Ning Dong and Chunting Zhou and Gargi Ghosh and Mike Lewis and Wen-tau Yih and Luke Zettlemoyer and Xi Victoria Lin},
title = {{Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models}},
journal = {Accepted by TMLR},
year = {2024},
url = {https://openreview.net/forum?id=Nu6N69i8SB},
}