中科院SNELLA：视觉模型微调新范式，性能超越SOTA，内存占用降低近40%
"参数高效微调" 相关文章
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction
LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
ChatGPT架构师，刚发布了最新研究成果
LoRA到底能否媲美全参？Thinking Machines用实验曲线划出「无悔区」
Thinking Machines曝LoRA终极指南：10倍学习率，媲美全参微调
LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts
Thinking Machines曝LoRA终极指南：10倍学习率，媲美全参微调
