Summary of Evaluating Quantized Large Language Models, by Shiyao Li et al.
Evaluating Quantized Large Language Models
by Shiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu, Xiangsheng Shi, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
First submitted to arxiv on: 28 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a comprehensive evaluation of post-training quantization (PTQ) on large language models (LLMs), aiming to reduce memory consumption and computational overhead. The authors evaluate the effect of PTQ on various model families, including OPT, LLaMA2, and others, with parameters ranging from 125M to 180B. Five types of tasks are considered: basic NLP, emergent ability, trustworthiness, dialogue, and long-context tasks. The evaluation also compares state-of-the-art quantization methods and provides recommendations for applying PTQ techniques. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making large language models smaller and more efficient. It does this by testing different ways to shrink the model’s memory usage while keeping its performance good. They tested many different models, each with a lot of parameters (125M to 180B), on five types of tasks. The results show which techniques work best for different types of tasks and provide guidance on how to apply these techniques in real-world scenarios. |
Keywords
» Artificial intelligence » Nlp » Quantization
