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/alex-f1tor/Image-Caption
https://github.com/alexa/alexa-prize-topical-chat-dataset
Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
https://github.com/alexa/alexa-with-dstc10-track2-dataset
"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
https://github.com/alexssanchez/unet-app-pucp
https://github.com/ali-nsua/quickRecommender
Yum-me: A Personalized Nutrient-based Meal Recommender System
https://github.com/alibaba-damo-academy/VCBench
Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
https://github.com/alibaba-nlp/webagent
https://github.com/alibaba/EasyNLP/tree/master/examples/knowledge_distillation
https://github.com/alibaba/EasyTransfer/tree/master/scripts/knowledge_distillation/adabert
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
https://github.com/alirezakazemipour/ppo-rnd
https://github.com/aliyun/qwen-dianjin
https://github.com/allen-li1231/treehop-rag
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
https://github.com/allenai/natural-instructions-expansion
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
https://github.com/allenai/scifact
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/alsgkals2/CoReD_Released
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
https://github.com/alsgkals2/cored
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
https://github.com/altndrr/persona
https://github.com/amazon-science/dq-bart
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization
https://github.com/amazon-science/intent-aware-encoder
Benchmarking Natural Language Understanding Services for building Conversational Agents
https://github.com/ambroggi/pruning-project-for-deep-neural-networks
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
https://github.com/amenra/ranx
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
https://github.com/aminekha/AI-For-2022
https://github.com/amir-hassan25/IdeaBench
IdeaBench: Benchmarking Large Language Models for Research Idea Generation
https://github.com/amirmansurian/attnfd
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation
https://github.com/amittiwary42/target-detection-eeg-signals
https://github.com/amkall/tcc_coco
COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting
https://github.com/amzn/xfer
https://github.com/andreamattiagaravagno/colabnas
https://github.com/andreped/livermask
https://github.com/andrey1908/mmdetection
https://github.com/andyreagan/sentiment-analysis-comparison-online-appendix
https://github.com/anissa218/medfair_ukbb
https://github.com/ankur-98/Multi-domain-Knowledge-Distillation
https://github.com/annabellachen/newDarknet
https://github.com/anonymouscode115/autoregressive_inference
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.