HouYi: An open-source large language model specially designed for renewable energy and carbon neutrality field
This provides a tool for researchers and practitioners in renewable energy and carbon neutrality to generate academic content, though it is incremental as it builds on existing LLMs with domain-specific data.
The paper tackled the lack of a specialized large language model for renewable energy by creating the first open-source dataset (REAP) from 1,168,970 academic papers and developing HouYi, a model that generates renewable energy academic paragraphs comparably to ChatGPT and outperforms other models like LLaMA-13B.
Renewable energy is important for achieving carbon neutrality goal. With the great success of Large Language Models (LLMs) like ChatGPT in automatic content generation, LLMs are playing an increasingly important role. However, there has not been a specially designed LLM for renewable energy. Meanwhile, there has not been any dataset of renewable energy for training LLMs. Therefore, this paper published the first open-source Renewable Energy Academic Paper (REAP) dataset for non-commercial LLM research of renewable energy. REAP dataset is collected through searching the title and abstract of 1,168,970 academic literatures from Web of Science. Based on REAP dataset, HouYi model, the first LLM for renewable energy, is developed through finetuning general LLMs. HouYi demonstrated powerful academic paper paragraph generation ability in renewable energy field. Experiments show that its ability to generate academic papers on renewable energy is comparable to ChatGPT, slightly outperforms Claude, ERNIE Bot and SparkDesk, and significantly outperforms open-source LLaMA-13B model.