{"repo":"MasterAI-EAM/Darwin","free":true,"listed":false,"github":"https://github.com/MasterAI-EAM/Darwin","clone":"git clone https://github.com/MasterAI-EAM/Darwin.git","description":"An open-source project dedicated to build foundational large language model for natural science, mainly in physics, chemistry and material science.","language":"Jupyter Notebook","stars":250,"topics":["chemistry","gpt","llm","material-design","physics"],"license":null,"category":"ai-agents","readme_excerpt":"Darwin: A Tailored GPT for the Scientific Domain 🇦🇺 Organization: University of New South Wales（UNSW) AI4Science & GreenDynamics AI Darwin is an open-source project dedicated to pretrain and fine-tune the LLaMA model on scientific literature and datasets. Specifically designed for the scientific domain with an emphasis on materials science, chemistry, and physics, Darwin integrates structured and unstructured scientific knowledge to enhance the efficacy of language models in scientific research. Usage and License Notices : Darwin is licensed and intended for research use only. The dataset is licensed under CC BY NC 4.0, allowing non-commercial use. Models trained using this dataset should not be used outside of research purposes. The weight diff is also under CC BY NC 4.0 license Update [2024.11.20] Key Achievements 1. Proved that Darwin’s fine-tuning strategies (QA + multi-task) substantially improve performance on diverse ML tasks. 2. Established Darwin as a competitive model, bridging the gap between specialized ML methods and large-scale generalist models like GPT-4. Model Performance Insights 1. Comparison of QA + Multi-task Strategies Across LLaMA Variants - Conducted extensive comparisons of QA and multi-task fine-tuning strategies on LLaMA1, LLaMA2, LLaMA3, and LLaMA3.1 models. - Finding: LLaMA1 with QA + multi-task fine-tuning achieves the best performance, outperforming all other variants. 2. Evaluation Against Other Models - Demonstrated that Darwin consistently ","default_branch":null,"files":null,"tree":[],"storefront":"/r/MasterAI-EAM","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/MasterAI-EAM/Darwin/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}