LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913264436248576 |
|---|---|
| author | Wu, Yichao Xiang, Yafei Huo, Shuning Gong, Yulu Liang, Penghao |
| author_facet | Wu, Yichao Xiang, Yafei Huo, Shuning Gong, Yulu Liang, Penghao |
| contents | In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the Low-Rank Adaptation(LoRA)framework. This method efficiently balances pre-trained knowledge retention and adaptability for task-specific optimizations. Through a randomized mechanism, LoRA-SP determines which parameters to update or freeze, significantly reducing computational and memory requirements without compromising model performance. We evaluated LoRA-SP across several benchmark NLP tasks, demonstrating its ability to achieve competitive performance with substantially lower resource consumption compared to traditional full-parameter fine-tuning and other parameter-efficient techniques. LoRA-SP innovative approach not only facilitates the deployment of advanced NLP models in resource-limited settings but also opens new research avenues into effective and efficient model adaptation strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08822 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models Wu, Yichao Xiang, Yafei Huo, Shuning Gong, Yulu Liang, Penghao Machine Learning Computation and Language In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the Low-Rank Adaptation(LoRA)framework. This method efficiently balances pre-trained knowledge retention and adaptability for task-specific optimizations. Through a randomized mechanism, LoRA-SP determines which parameters to update or freeze, significantly reducing computational and memory requirements without compromising model performance. We evaluated LoRA-SP across several benchmark NLP tasks, demonstrating its ability to achieve competitive performance with substantially lower resource consumption compared to traditional full-parameter fine-tuning and other parameter-efficient techniques. LoRA-SP innovative approach not only facilitates the deployment of advanced NLP models in resource-limited settings but also opens new research avenues into effective and efficient model adaptation strategies. |
| title | LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2403.08822 |