📑

AI Paper Research

AI 논문 조사 및 정리

Foundations
경량화·효율화Efficient AI
QLoRA: Efficient Finetuning of Quantized...AWQ: Activation-aware Weight Quantizatio...Fast Inference from Transformers via Spe...Efficient Memory Management for Large La...FlashAttention-2: Faster Attention with ...
Switch Transformers: Scaling to Trillion...FlashAttention: Fast and Memory-Efficien...GPTQ: Accurate Post-Training Quantizatio...
LoRA: Low-Rank Adaptation of Large Langu...
Distilling the Knowledge in a Neural Net...
홈/경량화·효율화/2015

경량화·효율화 — 2015

1편의 논문

NeurIPS 2014 Workshop15,000+

Distilling the Knowledge in a Neural Network

신경망의 지식 증류

Geoffrey Hinton, Oriol Vinyals, Jeff Dean (2015)

← 경량화·효율화 전체