metadata
license: apache-2.0
datasets:
- daven3/geosignal
- daven3/geobench
language:
- en
pipeline_tag: text2text-generation
tags:
- geoscience
Ge🌏Galactica: A Scientific Large Language Model in Geoscience
GeoGalactica is from further pre-training of Galactica -- a top-performing LLM trained with a large number of scientific documents.
Model Details
geobrain-ai/geogalactica shares the checkpoint at the 3/4 stage of the pre-training. And this repo shares the checkpoints of GeoGalactica during the first 3/4 of pre-training. If you want to access our model, you can contact us via email.
Model Description
- Developed by: Shanghai Jiao Tong University and Deep-time Digital Earth Science Center.
- Shared by [optional]: GeoBRAIN.ai
- Model type: Further pre-train and Supervised Fine-tuning
- Language(s) (NLP): English
- License: Apache License 2.0
- Finetuned from model: Galactica
Model Sources
- Repository: geobrain-ai/geogalactica
- Paper: GeoGalactica: A Scientific Large Language Model in Geoscience