Awesome Scientific Language Models
Awesome Scientific Language Models is a curated list of pre-trained language models for scientific domains such as mathematics, physics, chemistry, materials science, biology, medicine and geoscience, accompanying a survey paper on scientific large language models.
Awesome Scientific Language Models catalogs pre-trained language models built for scientific text and data, ranging from 100 million to 100 billion parameters and covering modalities such as language, graphs, vision, tables, molecules, proteins, genomes and climate time series. It accompanies the survey paper 'A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery' (EMNLP 2024) and is continuously updated.
Entries are organized by scientific domain, including general, mathematics, physics, chemistry and materials science, biology and medicine, and geography, geology and environmental science, and within each domain by modality. Each entry lists a paper's name, title, venue, and links to its paper, code and any released model, sorted chronologically, with a paper included only once it has named authors and a GitHub or Hugging Face link.
It is released under the MIT license and accepts community-suggested additions by email or pull request.