Training a seismic LLM from scratch
jzsfg · hn · 2026-07-13
The author mentions training a 113M parameter seismic LLM from scratch and has open-sourced the GitHub project: nanogpt-seis.
The core message here:
- It's not an application calling an existing large model
- It's a small-scale domain-specific language model trained from scratch
- The focus is on seismology/geophysics scenarios
The post itself is brief, but it's clearly an entry point for a reproducible experiment or open-source project.
More from Research
- Chinese AI labs are now treating distillation obfuscation as the top research topic — pmddomingos · 2026-07-22
- Structural ensembles beat single predictions in TCR:pMHC generalization study — quaidmorris · 2026-07-22
- RSS launches under OMSF to push structural biology data modeling at scale — MoAlQuraishi · 2026-07-22
- enFoldX tops 8 neoantigen scans and an unseen-peptide benchmark — quaidmorris · 2026-07-22
- enFoldX reaches AUC 0.82 on human VDJdb and transfers to mouse at 0.76 — quaidmorris · 2026-07-22
- enFoldX gains accuracy as AF3 ensemble disagreement rises for non-binders — quaidmorris · 2026-07-22