🪐 Introducing Galactica. A large language model for science. Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more. Explore and get weights: galactica.org
We believe models should be open. To accelerate science, we open source all models including the 120 billion model with no friction. You can access them here. github.com/paperswithcode…
We release our initial paper below. We train on a large scientific corpus of papers, reference material, knowledge bases and many other sources. Includes scientific text and also scientific modalities such as proteins, compounds and more. galactica.org/paper.pdf
@paperswithcode Love it, only wish there was an intermediate between the standard 6.7b and large 30b model.
@paperswithcode Is it possible that the dataset also be open?
@paperswithcode Hi, I was trying to fork your Github codes and run them on my local devices with the mini model. But it just bugs with 'CUDA error: invalid device ordinal'. I've tried ways to check and it seems that my env should be right set. I also try that on the Colab and it bugs as well.