Alert button
Picture for Zhuocheng Gong

Zhuocheng Gong

Alert button

What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation

Add code
Bookmark button
Alert button
Mar 11, 2024
Zhuocheng Gong, Jiahao Liu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan

Figure 1 for What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
Figure 2 for What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
Figure 3 for What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
Figure 4 for What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
Viaarxiv icon

Improving Input-label Mapping with Demonstration Replay for In-context Learning

Add code
Bookmark button
Alert button
Oct 30, 2023
Zhuocheng Gong, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan

Viaarxiv icon

PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models

Add code
Bookmark button
Alert button
May 30, 2023
Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan

Figure 1 for PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
Figure 2 for PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
Figure 3 for PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
Figure 4 for PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
Viaarxiv icon