snudm-starlab / SynQLinks
SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning (ICLR 2025)
☆28Updated 5 months ago
Alternatives and similar repositories for SynQ
Users that are interested in SynQ are comparing it to the libraries listed below
Sorting:
- SensiMix: Sensitivity-Aware 8-bit Index & 1-bit Value Mixed Precision Quantization for BERT Compression (PLOS One)☆34Updated 3 years ago
- Pea-KD: Parameter-efficient and accurate knowledge distillation on BERT (PLOS One)☆35Updated 2 years ago
- Flexible Convolutional Neural Network☆22Updated last year
- Sturctured pruning algorithm for pruning Transformer☆31Updated last year
- ☆33Updated 2 years ago
- PET: Parameter-efficient Knowledge Distillation on Transformer (PLOS One)☆15Updated 2 years ago
- Falcon: Lightweight and Accurate Convolution Based on Depthwise Separable Convolution (KAIS)☆44Updated 11 months ago
- Vector multiplication on Low-rank Matrix Factorization☆46Updated last year
- ☆56Updated 2 years ago
- ☆90Updated last year
- Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models (ICLR 2024)☆13Updated last month
- Review papers of NLP, mainly LLM.☆33Updated last year
- 2022_AAAI accepted paper, NaturalInversion:Data-Free Image Synthesis Improving Real-World Consistency☆10Updated 3 years ago
- The official NetsPresso Python package.☆45Updated 3 weeks ago
- A performance library for machine learning applications.☆184Updated last year
- 추천시스템 논문을 읽고 구현한 Code가 저장된 Repository☆66Updated 2 years ago
- PyTorch CoreSIG☆55Updated 6 months ago
- LaTeX 양식 : R&E, 졸업논문, beamer 등등 - 컴파일된 결과 pdf파일 미포함☆64Updated 4 months ago
- 제4회 AI × Bookathon 우수상☆14Updated 2 years ago
- 추천 시스템 관련 자료 모음☆83Updated last year
- 언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.☆426Updated 3 months ago
- ☆27Updated 4 months ago
- ☆54Updated 8 months ago
- OwLite is a low-code AI model compression toolkit for AI models.☆46Updated 2 months ago
- <파이토치로 배우는 자연어 처리>(한빛미디어, 2021)의 소스 코드를 위한 저장소입니다.☆132Updated 11 months ago
- ☆23Updated 10 months ago
- Compressed LLMs for Efficient Text Generation [ICLR'24 Workshop]☆84Updated 10 months ago
- Instruct-tune LLaMA on consumer hardware☆15Updated 2 years ago
- KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)☆292Updated 9 months ago
- ☆10Updated 2 years ago