DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model
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_ | 1866910402376368128 |
|---|---|
| author | Gao, Chao Zhang, Sai Qian |
| author_facet | Gao, Chao Zhang, Sai Qian |
| contents | To enhance the performance of large language models (LLM) on downstream tasks, one solution is to fine-tune certain LLM parameters and make it better align with the characteristics of the training dataset. This process is commonly known as parameter-efficient fine-tuning (PEFT). Due to the scale of LLM, PEFT operations are usually executed in the public environment (e.g., cloud server). This necessitates the sharing of sensitive user data across public environments, thereby raising potential privacy concerns. To tackle these challenges, we propose a distributed PEFT framework called DLoRA. DLoRA enables scalable PEFT operations to be performed collaboratively between the cloud and user devices. Coupled with the proposed Kill and Revive algorithm, the evaluation results demonstrate that DLoRA can significantly reduce the computation and communication workload over the user devices while achieving superior accuracy and privacy protection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05182 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model Gao, Chao Zhang, Sai Qian Machine Learning Artificial Intelligence Computation and Language Distributed, Parallel, and Cluster Computing To enhance the performance of large language models (LLM) on downstream tasks, one solution is to fine-tune certain LLM parameters and make it better align with the characteristics of the training dataset. This process is commonly known as parameter-efficient fine-tuning (PEFT). Due to the scale of LLM, PEFT operations are usually executed in the public environment (e.g., cloud server). This necessitates the sharing of sensitive user data across public environments, thereby raising potential privacy concerns. To tackle these challenges, we propose a distributed PEFT framework called DLoRA. DLoRA enables scalable PEFT operations to be performed collaboratively between the cloud and user devices. Coupled with the proposed Kill and Revive algorithm, the evaluation results demonstrate that DLoRA can significantly reduce the computation and communication workload over the user devices while achieving superior accuracy and privacy protection. |
| title | DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model |
| topic | Machine Learning Artificial Intelligence Computation and Language Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2404.05182 |