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/deezer/interpretable_nn_attribution
공식 코드Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction
https://github.com/dice-group/lola
공식 코드LOLA -- An Open-Source Massively Multilingual Large Language Model
https://github.com/divelab/AIRS
공식 코드A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling
https://github.com/dlyuangod/mlp-kan
공식 코드https://github.com/dmis-lab/monet
공식 코드https://github.com/dreamzz5/st-expert
공식 코드https://github.com/dreasysnail/RetGen
공식 코드RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling
https://github.com/dtuzi123/LifelongMixtureVAEs
공식 코드https://github.com/duterscmy/cd-moe
공식 코드Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
https://github.com/dvmazur/mixtral-offloading
공식 코드Fast Inference of Mixture-of-Experts Language Models with Offloading
https://github.com/ecolab-nus/DAOP
공식 코드DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference
https://github.com/edshieh/motionprediction
공식 코드https://github.com/edvinli/federated-learning-mixture
공식 코드https://github.com/eezkni/ssiu
공식 코드Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution
https://github.com/efeslab/fiddler
공식 코드Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
https://github.com/emzucas/minidrive
공식 코드https://github.com/enflametechnology/deepspeed
공식 코드MoNTA: Accelerating Mixture-of-Experts Training with Network-Traffc-Aware Parallel Optimization
https://github.com/enkhtogtokh/voicegrpo
공식 코드https://github.com/epfl-ml4ed/interpretcc
공식 코드Intrinsic User-Centric Interpretability through Global Mixture of Experts
https://github.com/epfml/comigs
공식 코드On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
https://github.com/ericssonresearch/fl-moe
공식 코드Adaptive Expert Models for Personalization in Federated Learning
https://github.com/espnet/espnet
공식 코드Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation
https://github.com/etesami/MOE-FL
공식 코드https://github.com/event-ahu/openevdet
공식 코드https://github.com/facebookresearch/fairseq
공식 코드No Language Left Behind: Scaling Human-Centered Machine Translation
https://github.com/facebookresearch/stopes
공식 코드No Language Left Behind: Scaling Human-Centered Machine Translation
https://github.com/facico/goat-peft
공식 코드https://github.com/fe1ixxu/lms_fd
공식 코드Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
https://github.com/fe1ixxu/stratified_mixture_of_experts
공식 코드Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
https://github.com/ffmpbgrnn/yt8m
공식 코드https://github.com/fighoture/moe_unsupervised_pruning
공식 코드Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models
https://github.com/fiveai/MoCaE
공식 코드MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
https://github.com/flipkart-incubator/kd-dae
공식 코드https://github.com/for-ai/parameter-efficient-moe
공식 코드Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
https://github.com/freedomintelligence/apollomoe
공식 코드Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.