Hairu Wang
2024
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
Deyuan Liu
|
Zhanyue Qin
|
Hairu Wang
|
Zhao Yang
|
Zecheng Wang
|
Fangying Rong
|
Qingbin Liu
|
Yanchao Hao
|
Bo Li
|
Xi Chen
|
Cunhang Fan
|
Zhao Lv
|
Dianhui Chu
|
Zhiying Tu
|
Dianbo Sui
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
While large language models (LLMs) excel in many domains, their complexity and scale challenge deployment in resource-limited environments. Current compression techniques, such as parameter pruning, often fail to effectively utilize the knowledge from pruned parameters. To address these challenges, we propose Manifold-Based Knowledge Alignment and Layer Merging Compression (MKA), a novel approach that uses manifold learning and the Information Bottleneck (IB) measure to merge similar layers, reducing model size while preserving essential performance. We evaluate MKA on multiple benchmark datasets and various LLMs. Our findings show that MKA not only preserves model performance but also achieves substantial compression ratios, outperforming traditional pruning methods. Moreover, when coupled with quantization, MKA delivers even greater compression. Specifically, on the MMLU dataset using the Llama3-8B model, MKA achieves a compression ratio of 43.75% with a minimal performance decrease of only 2.82%. The proposed MKA method offers a resource-efficient and performance-preserving model compression technique for LLMs. We make our code available at https://github.com/SempraETY/Pruning-via-Merging
Search
Co-authors
- Deyuan Liu 1
- Zhanyue Qin 1
- Zhao Yang 1
- Zecheng Wang 1
- Fangying Rong 1
- show all...