1
Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
联邦学习遇上LoRA新框架，专治大模型在异构设备上协作微调的痛点，方案灵活高效。
arXiv:2501.19389v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on resource-constrained clients remains a challenging pro…