Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.08001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909167278620672 |
|---|---|
| author | Zhang, Zhengde Zhang, Yiyu Yao, Haodong Luo, Jianwen Zhao, Rui Huang, Bo Zhao, Jiameng Liao, Yipu Li, Ke Zhao, Lina Cao, Jun Qi, Fazhi Yuan, Changzheng |
| author_facet | Zhang, Zhengde Zhang, Yiyu Yao, Haodong Luo, Jianwen Zhao, Rui Huang, Bo Zhao, Jiameng Liao, Yipu Li, Ke Zhao, Lina Cao, Jun Qi, Fazhi Yuan, Changzheng |
| contents | Large Language Models (LLMs) are undergoing a period of rapid updates and changes, with state-of-the-art (SOTA) model frequently being replaced. When applying LLMs to a specific scientific field, it's challenging to acquire unique domain knowledge while keeping the model itself advanced. To address this challenge, a sophisticated large language model system named as Xiwu has been developed, allowing you switch between the most advanced foundation models and quickly teach the model domain knowledge. In this work, we will report on the best practices for applying LLMs in the field of high-energy physics (HEP), including: a seed fission technology is proposed and some data collection and cleaning tools are developed to quickly obtain domain AI-Ready dataset; a just-in-time learning system is implemented based on the vector store technology; an on-the-fly fine-tuning system has been developed to facilitate rapid training under a specified foundation model. The results show that Xiwu can smoothly switch between foundation models such as LLaMA, Vicuna, ChatGLM and Grok-1. The trained Xiwu model is significantly outperformed the benchmark model on the HEP knowledge question-and-answering and code generation. This strategy significantly enhances the potential for growth of our model's performance, with the hope of surpassing GPT-4 as it evolves with the development of open-source models. This work provides a customized LLM for the field of HEP, while also offering references for applying LLM to other fields, the corresponding codes are available on Github. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08001 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics Zhang, Zhengde Zhang, Yiyu Yao, Haodong Luo, Jianwen Zhao, Rui Huang, Bo Zhao, Jiameng Liao, Yipu Li, Ke Zhao, Lina Cao, Jun Qi, Fazhi Yuan, Changzheng High Energy Physics - Phenomenology Artificial Intelligence Computation and Language Machine Learning High Energy Physics - Experiment Computational Physics I.2.7 Large Language Models (LLMs) are undergoing a period of rapid updates and changes, with state-of-the-art (SOTA) model frequently being replaced. When applying LLMs to a specific scientific field, it's challenging to acquire unique domain knowledge while keeping the model itself advanced. To address this challenge, a sophisticated large language model system named as Xiwu has been developed, allowing you switch between the most advanced foundation models and quickly teach the model domain knowledge. In this work, we will report on the best practices for applying LLMs in the field of high-energy physics (HEP), including: a seed fission technology is proposed and some data collection and cleaning tools are developed to quickly obtain domain AI-Ready dataset; a just-in-time learning system is implemented based on the vector store technology; an on-the-fly fine-tuning system has been developed to facilitate rapid training under a specified foundation model. The results show that Xiwu can smoothly switch between foundation models such as LLaMA, Vicuna, ChatGLM and Grok-1. The trained Xiwu model is significantly outperformed the benchmark model on the HEP knowledge question-and-answering and code generation. This strategy significantly enhances the potential for growth of our model's performance, with the hope of surpassing GPT-4 as it evolves with the development of open-source models. This work provides a customized LLM for the field of HEP, while also offering references for applying LLM to other fields, the corresponding codes are available on Github. |
| title | Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics |
| topic | High Energy Physics - Phenomenology Artificial Intelligence Computation and Language Machine Learning High Energy Physics - Experiment Computational Physics I.2.7 |
| url | https://arxiv.org/abs/2404.08001 |