Reconstruct the Pruned Model without Any Retraining
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916329390342144 |
|---|---|
| author | Wang, Pingjie Fan, Ziqing Hu, Shengchao Chen, Zhe Wang, Yanfeng Wang, Yu |
| author_facet | Wang, Pingjie Fan, Ziqing Hu, Shengchao Chen, Zhe Wang, Yanfeng Wang, Yu |
| contents | Structured pruning is a promising hardware-friendly compression technique for large language models (LLMs), which is expected to be retraining-free to avoid the enormous retraining cost. This retraining-free paradigm involves (1) pruning criteria to define the architecture and (2) distortion reconstruction to restore performance. However, existing methods often emphasize pruning criteria while using reconstruction techniques that are specific to certain modules or criteria, resulting in limited generalizability. To address this, we introduce the Linear Interpolation-based Adaptive Reconstruction (LIAR) framework, which is both efficient and effective. LIAR does not require back-propagation or retraining and is compatible with various pruning criteria and modules. By applying linear interpolation to the preserved weights, LIAR minimizes reconstruction error and effectively reconstructs the pruned output. Our evaluations on benchmarks such as GLUE, SQuAD, WikiText, and common sense reasoning show that LIAR enables a BERT model to maintain 98% accuracy even after removing 50% of its parameters and achieves top performance for LLaMA in just a few minutes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reconstruct the Pruned Model without Any Retraining Wang, Pingjie Fan, Ziqing Hu, Shengchao Chen, Zhe Wang, Yanfeng Wang, Yu Machine Learning Structured pruning is a promising hardware-friendly compression technique for large language models (LLMs), which is expected to be retraining-free to avoid the enormous retraining cost. This retraining-free paradigm involves (1) pruning criteria to define the architecture and (2) distortion reconstruction to restore performance. However, existing methods often emphasize pruning criteria while using reconstruction techniques that are specific to certain modules or criteria, resulting in limited generalizability. To address this, we introduce the Linear Interpolation-based Adaptive Reconstruction (LIAR) framework, which is both efficient and effective. LIAR does not require back-propagation or retraining and is compatible with various pruning criteria and modules. By applying linear interpolation to the preserved weights, LIAR minimizes reconstruction error and effectively reconstructs the pruned output. Our evaluations on benchmarks such as GLUE, SQuAD, WikiText, and common sense reasoning show that LIAR enables a BERT model to maintain 98% accuracy even after removing 50% of its parameters and achieves top performance for LLaMA in just a few minutes. |
| title | Reconstruct the Pruned Model without Any Retraining |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.13331 |