Tag: Parameter-Efficient Fine-Tuning

All the papers with the tag "Parameter-Efficient Fine-Tuning".

• HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models

  grok-3-latest

  Score: 0.77

  Published:2025年5月5日 at  at 17:09

  #LLM, #Parameter-Efficient Fine-Tuning, #Split Learning, #Heterogeneous Computing, #Adaptation

  HSplitLoRA 提出了一种异构参数高效微调框架，通过重要权重识别、自适应秩与模型分割配置及无噪声适配器聚合，显著提升了大型语言模型在异构环境下的微调性能和效率。