# LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

arXiv: https://arxiv.org/abs/2406.16554 · HTML: https://mlsanity.com/paper/2406.16554/

## Key facts

- Cited by 123 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining](https://mlsanity.com/paper/2305.10429/) (2023)
- [What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning](https://mlsanity.com/paper/2312.15685/) (2023)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [Hash Layers For Large Sparse Models](https://mlsanity.com/paper/2106.04426/) (2021)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints](https://mlsanity.com/paper/2212.05055/) (2022)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [MoEfication: Transformer Feed-forward Layers are Mixtures of Experts](https://mlsanity.com/paper/2110.01786/) (2021)
- [A Review of Sparse Expert Models in Deep Learning](https://mlsanity.com/paper/2209.01667/) (2022)

## Built on by (most cited first, 30 of 123)

- [A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://mlsanity.com/paper/2503.21614/) (2025)
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024)
- [DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving](https://mlsanity.com/paper/2505.16278/) (2025)
- [MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts](https://mlsanity.com/paper/2410.07348/) (2024)
- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [MoM: Linear Sequence Modeling with Mixture-of-Memories](https://mlsanity.com/paper/2502.13685/) (2025)
- [Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback](https://mlsanity.com/paper/2501.12895/) (2025)
- [Advancing Expert Specialization for Better MoE](https://mlsanity.com/paper/2505.22323/) (2025)
- [Liger: Linearizing Large Language Models to Gated Recurrent Structures](https://mlsanity.com/paper/2503.01496/) (2025)
- [ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews](https://mlsanity.com/paper/2503.08506/) (2025)
- [LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training](https://mlsanity.com/paper/2411.15708/) (2024)
- [CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling](https://mlsanity.com/paper/2409.19291/) (2024)
- [A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models](https://mlsanity.com/paper/2410.07265/) (2024)
- [Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment](https://mlsanity.com/paper/2502.16894/) (2025)
- [MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts](https://mlsanity.com/paper/2510.27234/) (2025)
- [D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving](https://mlsanity.com/paper/2504.15299/) (2025)
- [LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes](https://mlsanity.com/paper/2501.04004/) (2025)
- [VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models](https://mlsanity.com/paper/2503.07478/) (2025)
- [Recurrent Knowledge Identification and Fusion for Language Model Continual Learning](https://mlsanity.com/paper/2502.17510/) (2025)
- [Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts](https://mlsanity.com/paper/2503.05066/) (2025)
- [What You Have is What You Track: Adaptive and Robust Multimodal Tracking](https://mlsanity.com/paper/2507.05899/) (2025)
- [SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?](https://mlsanity.com/paper/2411.18797/) (2024)
- [H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs](https://mlsanity.com/paper/2411.17792/) (2024)
- [SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling](https://mlsanity.com/paper/2506.04179/) (2025)
- [DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs](https://mlsanity.com/paper/2407.11030/) (2024)
- [MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios](https://mlsanity.com/paper/2409.16084/) (2024)
- [ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning](https://mlsanity.com/paper/2501.15316/) (2025)
- [EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization](https://mlsanity.com/paper/2506.13329/) (2025)
- [ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts](https://mlsanity.com/paper/2510.17483/) (2025)
- [HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies](https://mlsanity.com/paper/2512.05693/) (2025)

## Abstract (arXiv)

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, training MoE from scratch in a large-scale setting still suffers from data-hungry and instability problems. Motivated by this limit, we investigate building MoE models from existing dense large language models. Specifically, based on the well-known LLaMA-2 7B model, we obtain an MoE model by: (1) Expert Construction, which partitions the parameters of original Feed-Forward Networks (FFNs) into multiple experts; (2) Continual Pre-training, which further trains the transformed MoE model and additional gate networks. In this paper, we comprehensively explore different methods for expert construction and various data sampling strategies for continual pre-training. After these stages, our LLaMA-MoE models could maintain language abilities and route the input tokens to specific experts with part of the parameters activated. Empirically, by training 200B tokens, LLaMA-MoE-3.5B models significantly outperform dense models that contain similar activation parameters. The source codes and models are available at https://github.com/pjlab-sys4nlp/llama-moe .