🔬
🔬 Science
Developer trains 113M-parameter LLM from scratch to predict earthquakes
A developer built a 113-million-parameter language model from scratch, based on the NanoGPT architecture, specifically trained on seismic data to analyse earthquake patterns. The project, called nanogpt-seis, is published on GitHub as an experiment bridging large language model techniques with seismology. It represents an unconventional application of LLM methods outside their usual text-processing domain.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!