https://github.com/opensparsellms/llama-moe-v2
공식 코드LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
Papers with Code 아카이브
Mixture-of-Experts
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/osayamenja/aristos
공식 코드https://github.com/osayamenja/kleos
공식 코드https://github.com/padas-lab-de/multi-language-dataset-creator
공식 코드https://github.com/paragonlight/meteor-of-lora
공식 코드MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models
https://github.com/pauzii/phasebetweener
공식 코드https://github.com/pbelcak/fastfeedforward
공식 코드https://github.com/pidinosaur2804/wave-cre-plus-plus
공식 코드https://github.com/piotrpiekos/MoSA
공식 코드Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing
https://github.com/pjlab-sys4nlp/llama-moe
공식 코드LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
https://github.com/pkasela/desire-me
공식 코드DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts
https://github.com/pku-sec-lab/adapmoe
공식 코드AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
https://github.com/pku-sec-lab/hybrimoe
공식 코드HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
https://github.com/pku-yuangroup/chatlaw
공식 코드https://github.com/prismformore/multi-task-transformer
공식 코드TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
https://github.com/qihao-duan/janusdna
공식 코드JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
https://github.com/qiuzh20/gated_attention
공식 코드Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
https://github.com/qiuzh20/rmoe
공식 코드https://github.com/quanshr/dmoerm
공식 코드DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling
https://github.com/qwenlm/qwen2
공식 코드https://github.com/qwenlm/qwen2.5
공식 코드https://github.com/rachtsy/molex
공식 코드MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling
https://github.com/rachtsy/momentumsmoe
공식 코드MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
https://github.com/raina-xin/i2moe
공식 코드I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts
https://github.com/rando11199/latentprototyperouter
공식 코드Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts
https://github.com/ranggihwang/pregated_moe
공식 코드Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference
https://github.com/remigenet/kamoe
공식 코드A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Experts
https://github.com/rhymes-ai/aria
공식 코드https://github.com/ringbdstack/stamimupter
공식 코드STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation
https://github.com/robertcsordas/moe_attention
공식 코드SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
https://github.com/robertcsordas/moeut
공식 코드https://github.com/robertcsordas/switchhead
공식 코드SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
https://github.com/rogerni/mole
공식 코드Mixture-of-Linear-Experts for Long-term Time Series Forecasting
https://github.com/royalskye/routing-mvmoe
공식 코드MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
https://github.com/royzry98/moase-pytorch
공식 코드https://github.com/rsmath/ensemble-deeponet
공식 코드Ensemble and Mixture-of-Experts DeepONets For Operator Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.