A demo version of Meta's 'Galactica' language model for scientific papers was released this week, which integrates simple text prompts to summarize academic literature, solve math problems, and generate Wiki articles. This was released by Papers with code along with Meta.

As explained by Galactica:

Galactica models are trained on a large corpus comprising more than 360 millions in-context citations and over 50 millions of unique references normalized across a diverse set of sources. This enables Galactica to suggest citations and help discover related papers.

From Yann LeCun:

According to the site:

Galactica models are trained on a large corpus comprising more than 360 millions in-context citations and over 50 millions of unique references normalized across a diverse set of sources. This enables Galactica to suggest citations and help discover related papers.

Sample for citation:

From equation:

From summary:

From natural language:

It has other features like:

  • converting python code to mathematics
  • converting mathematics code to plain English
  • simplify a python code

among other

More Resources:

Paper: https://galactica.org/static/paper.pdf

Website: https://galactica.org/

Code: https://github.com/paperswithcode/galai


If you like our work, please consider supporting us so we can keep doing what we do. And as a current subscriber, enjoy this nice discount!

Also: if you haven’t yet, follow us on Twitter, TikTok, or YouTube!