---
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](https://huggingface.co/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](mailto:davendw@sjtu.edu.cn).

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** Shanghai Jiao Tong University and Deep-time Digital Earth Science Center.
- **Shared by [optional]:** [GeoBRAIN.ai](https://www.geobrain-ai.com/)
- **Model type:** Further pre-train and Supervised Fine-tuning
- **Language(s) (NLP):** English
- **License:** Apache License 2.0
- **Finetuned from model:** [Galactica](https://huggingface.co/facebook/galactica-30b)

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [geobrain-ai/geogalactica](https://github.com/geobrain-ai/geogalactica)
- **Paper:** [GeoGalactica: A Scientific Large Language Model in Geoscience](#)

## Citation