Self-calibration for Language Model Quantization and Pruning
Williams, Miles, Chrysostomou, George, Aletras, Nikolaos
–arXiv.org Artificial Intelligence
Quantization and pruning are fundamental approaches for model compression, enabling efficient inference for language models. In a post-training setting, state-of-the-art quantization and pruning methods require calibration data, a small set of unlabeled examples. Conventionally, randomly sampled web text is used, aiming to reflect the model training data. However, this poses two key problems: (1) unrepresentative calibration examples can harm model performance, and (2) organizations increasingly avoid releasing model training data. In this paper, we propose self-calibration as a solution. Our approach requires no external data, instead leveraging the model itself to generate synthetic calibration data as a better approximation of the pre-training data distribution. We extensively compare the performance of self-calibration with several baselines, across a variety of models, compression methods, and tasks. Our approach proves consistently competitive in maximizing downstream task performance, frequently outperforming even using real data.
arXiv.org Artificial Intelligence
Oct-22-2024
- Country:
- North America
- Dominican Republic (0.04)
- United States
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California > San Diego County
- San Diego (0.04)
- New York > New York County
- Canada > Ontario
- Toronto (0.04)
- Europe
- Monaco (0.04)
- Germany > Berlin (0.04)
- United Kingdom > England
- South Yorkshire > Sheffield (0.04)
- Spain > Valencian Community
- Valencia Province > Valencia (0.04)
- Italy > Tuscany
- Florence (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Asia
- Singapore (0.04)
- China (0.04)
- British Indian Ocean Territory > Diego Garcia (0.04)
- Thailand > Bangkok
- Bangkok (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- Middle East
- Jordan (0.04)
- Israel (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Saudi Arabia > Asir Province
- Abha (0.04)
- Japan
- Kyūshū & Okinawa > Kyūshū
- Miyazaki Prefecture > Miyazaki (0.04)
- Honshū > Chūbu
- Toyama Prefecture > Toyama (0.04)
- Kyūshū & Okinawa > Kyūshū
- Africa
- Sudan (0.04)
- Zambia > Southern Province
- Choma (0.04)
- North America
- Genre:
- Research Report > New Finding (0.45)
- Industry:
- Information Technology (0.46)
- Technology: