https://github.com/jquesnelle/yarn
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
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/kaiyangzhou/on-device-dg
https://github.com/kaung-htet-myat/Multi-teachers-Knowledge-Distillation
https://github.com/keke921/gclloss
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
https://github.com/keke921/gnm-pt
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
https://github.com/keke921/h2t
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
https://github.com/knotgrass/Knowledge-Distillation
https://github.com/labmlai/annotated_deep_learning_paper_implementations
https://github.com/learning-at-home/hivemind
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts
https://github.com/lingjzhu/charsiug2p
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
https://github.com/lingyucai/Distilling-the-Knowledge-in-a-Neural-Network
https://github.com/lucidrains/mixture-of-experts
GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
https://github.com/lucidrains/soft-moe-pytorch
RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
https://github.com/ma921/XRDidentifier
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
https://github.com/markliou/model_distillation
https://github.com/mckunkel/DistillingObjectDetector
https://github.com/miccunifi/arniqa
Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild
https://github.com/microsoft/deepspeed-mii
DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
https://github.com/microsoft/torchscale
https://github.com/mkavim/finetune_bert
https://github.com/multi-swe-bench/magentless
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
https://github.com/multi-swe-bench/mopenhands
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
https://github.com/multi-swe-bench/mswe-agent
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
https://github.com/mv96/mm_extraction
https://github.com/nvidia/ruler
https://github.com/openlamm/lamm
Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
https://github.com/oppo-us-research/riav-mvs
Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks
https://github.com/paddlepaddle/edl
https://github.com/paperstiger/MoE-public
Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts
https://github.com/phixion/phixion
https://github.com/pku-yuangroup/chat-univi
MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
https://github.com/pra-dan/Worth-Reading-ML-Papers
https://github.com/pwc-1/Paper-10/tree/main/switch_transformers
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
https://github.com/pwc-1/Paper-5/tree/main/mixtral
Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral
https://github.com/pwc-1/Paper-8/tree/main/deepseek_v2
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
https://github.com/pwc-1/Paper-9/tree/main/2/mixtral
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.