https://github.com/alibaba/EasyNLP
공식 코드Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains
Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 90
Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/alibaba/cloudeval-yaml
공식 코드CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation
https://github.com/alibaba/easyrobust/tree/main/benchmarks/imagenet-e
공식 코드ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
https://github.com/alibaba/federatedscope
공식 코드FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization
https://github.com/alibabaresearch/damo-convai
공식 코드https://github.com/alice1998/urs
공식 코드A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models
https://github.com/alihanhyk/invconban
공식 코드Inverse Contextual Bandits: Learning How Behavior Evolves over Time
https://github.com/alimenati/PowerMamba
공식 코드https://github.com/alinlab/cs-kd
공식 코드Regularizing Class-wise Predictions via Self-knowledge Distillation
https://github.com/alipay/vcsl
공식 코드https://github.com/aliprf/kd-loss
공식 코드Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks
https://github.com/alirezasalemi7/dedr-mm-fid
공식 코드https://github.com/alisafaya/mukayese
공식 코드https://github.com/aliyun/cflue
공식 코드https://github.com/alldbi/SuperMix
공식 코드https://github.com/allenai/discoveryworld
공식 코드https://github.com/allenai/disturb-free
공식 코드https://github.com/allenai/natural-instructions
공식 코드Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
https://github.com/allenai/plasma
공식 코드https://github.com/allenai/robustnav
공식 코드RobustNav: Towards Benchmarking Robustness in Embodied Navigation
https://github.com/allenai/wildbench
공식 코드WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
https://github.com/allenai/wimbd
공식 코드https://github.com/alloydas/fast-textspotter
공식 코드FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
https://github.com/alonso130r/knowledge-distillation
공식 코드Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting
https://github.com/alpha-vllm/llama2-accessory
공식 코드SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
https://github.com/alphadl/rlfw-nat
공식 코드Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation
https://github.com/alphafin-proj/alphafin
공식 코드AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework
https://github.com/alsace08/sumcot
공식 코드https://github.com/altndrr/apex
공식 코드Automatic benchmarking of large multimodal models via iterative experiment programming
https://github.com/altoslabs/perturbench
공식 코드PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis
https://github.com/alvin-zeng/temporal-robustness-benchmark
공식 코드Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
https://github.com/amahdeej/sc2-edge-learning
공식 코드https://github.com/amayuelas/NNKGReasoning
공식 코드https://github.com/amazon-research/dq-bart
공식 코드DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization
https://github.com/amazon-research/question-answer-consolidation
공식 코드https://github.com/amazon-science/PrefEval
공식 코드Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.