Summary of Phonelm:an Efficient and Capable Small Language Model Family Through Principled Pre-training, by Rongjie Yi and Xiang Li and Weikai Xie and Zhenyan Lu and Chenghua Wang and Ao Zhou and Shangguang Wang and Xiwen Zhang and Mengwei Xu
PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training
by Rongjie Yi, Xiang Li, Weikai Xie, Zhenyan Lu, Chenghua Wang, Ao Zhou, Shangguang Wang, Xiwen Zhang, Mengwei Xu
First submitted to arxiv on: 7 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 The paper presents a new principle for designing small language models (SLMs) that prioritize runtime efficiency, specifically for on-device deployment. This approach is demonstrated through the development of PhoneLM SLM family, which achieves state-of-the-art capability-efficiency tradeoffs among comparable models. The authors release open-source code, weights, and training datasets to ensure reproducibility and transparency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to design small language models that think about how fast they will run on devices. They make a family of SLMs called PhoneLM that do really well compared to others with the same amount of data. The authors share all their code, model weights, and training data so other researchers can use it. |
