LoRA中到底有多少参数冗余？新研究：砍掉95%都能保持高性能
"参数高效微调" 相关文章
CVPR 2025 | CV 微调卷出天际，Mona：我小、我强、我省资源
CVPR25 | CV 微调卷出天际，Mona：我小，我强，我省资源
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
北大团队提出LIFT：将长上下文知识注入模型参数，提升大模型长文本能力
This AI Paper Introduces a Parameter-Efficient Fine-Tuning Framework: LoRA, QLoRA, and Test-Time Scaling for Optimized LLM Performance
PEFT fine tuning of Llama 3 on SageMaker HyperPod with AWS Trainium
一篇AI冬令营第一期的优秀学习笔记！
一篇AI冬令营第一期的优秀学习笔记！
【NLP】Kaggle知识点：文本分类与LoRA
PointGST：点云分析精度卷到99%了，还只用了2M训练参数
NeurIPS 2024 Oral | 小参数，大作为！揭秘非对称 LoRA 架构的高效性能
如何微调（Fine-tuning）大语言模型？
CRISPR-Cas9 guide RNA efficiency prediction with efficiently tuned models in Amazon SageMaker
LoRA-Pro: A Groundbreaking Machine Learning Approach to Bridging the Performance Gap Between Low-Rank Adaptation and Full Fine-Tuning
仅微调0.02%参数，性能接近全量微调！上交大推出高效微调统一新范式
A Paradigm Shift: MoRA’s Role in Advancing Parameter-Efficient Fine-Tuning Techniques
