paper-with-me

Papers

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts

2024-08-15 · Qizhen Zhang, Nikolas Gritsch, Dwaraknath Gnaneshwar, Simon Guo, David Cairuz, Bharat Venkitesh, Jakob Foerster, Phil Blunsom, Sebastian Ruder, Ahmet Ustun, Acyr Locatelli

The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive. Existing methods mitigate this by pre-training multiple dense expert models independently and using them to initialize an MoE. This is done by using experts' feed-forward network (FFN) to initialize the MoE's experts while merging other parameters. However, this method limits the reuse of dense model parameters to only the FFN layers, thereby constraining the advantages when "upcycling" these models into MoEs. We propose BAM (Branch-Attend-Mix), a simple yet effective method that addresses this shortcoming. BAM makes full use of specialized dense models by not only using their FFN to initialize the MoE layers but also leveraging experts' attention parameters fully by initializing them into a soft-variant of Mixture of Attention (MoA) layers. We explore two methods for upcycling attention parameters: 1) initializing separate attention experts from dense models including all attention parameters for the best model performance; and 2) sharing key and value parameters across all experts to facilitate for better inference efficiency. To further improve efficiency, we adopt a parallel attention transformer architecture to MoEs, which allows the attention experts and FFN experts to be computed concurrently. Our experiments on seed models ranging from 590 million to 2 billion parameters demonstrate that BAM surpasses baselines in both perplexity and downstream task performance, within the same computational and data constraints.

📄 PDF Abstract BibTeX arXiv:2408.08274

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-Experts

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
MoE 설명 없음
BAM Park et al. proposed the bottleneck attention module (BAM), aiming to efficiently improve the representational capability of networks. It uses dilated convolution to enlarge…

Similar Papers 제목 키워드 기반

Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling

2025-08-31 · Junfeng Ran, Guangxiang Zhao, Yuhan Wu, Dawei Zhu 외 arxiv

The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. However, efficiently training these models re…

Upcycling Large Language Models into Mixture of Experts

2024-10-10 · Ethan He, Abhinav Khattar, Ryan Prenger, Vijay Korthikanti 외

Upcycling pre-trained dense language models into sparse mixture-of-experts (MoE) models is an efficient approach to increase the model capacity of already trained models. However, optimal techniques for upcycling at scal…

Mixture-of-ExpertsMMLU

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling

2025-02-03 · Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen 외

Mixture-of-Experts (MoE) models are crucial for scaling model capacity while controlling inference costs. While integrating MoE into multimodal models like CLIP improves performance, training these models is notoriously …

Mixture-of-Experts

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

2025-02-26 · Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda 외

The Mixture of Experts (MoE) architecture reduces the training and inference cost significantly compared to a dense model of equivalent capacity. Upcycling is an approach that initializes and trains an MoE model using a …

Mixture-of-Experts

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging

2024-10-02 · Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Yu Sun 외

Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to …

DiversityMixture-of-Experts