Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# AG4Masses: AlphaGeometry for the Masses
|
2 |
|
3 |
An exciting recent development in AI with rigorous logical reasoning ability is the [AlphaGeometry](https://www.nature.com/articles/s41586-023-06747-5) system developed by Google Deepmind. Google made the source code for running AlphaGeometry available on GitHub at [google-deepmind/alphageometry](https://github.com/google-deepmind/alphageometry). However, the AlphaGeometry system as Google released, with the Language Model trained by Google, still requires a tremendous amount of computing power to run when solving problems. As Google's paper mentioned, in order to solve IMO level problems in about 1.5 hour, it needed 4 GPU V100 and up to 250 CPUs. These are not the kind of hardware casual users and hobbyists have access to.
|
|
|
1 |
+
---
|
2 |
+
title: AlphaGeometry Jupyter
|
3 |
+
emoji: 💻🐳
|
4 |
+
colorFrom: gray
|
5 |
+
colorTo: green
|
6 |
+
sdk: docker
|
7 |
+
pinned: false
|
8 |
+
tags:
|
9 |
+
- jupyterlab
|
10 |
+
suggested_storage: small
|
11 |
+
---
|
12 |
+
|
13 |
# AG4Masses: AlphaGeometry for the Masses
|
14 |
|
15 |
An exciting recent development in AI with rigorous logical reasoning ability is the [AlphaGeometry](https://www.nature.com/articles/s41586-023-06747-5) system developed by Google Deepmind. Google made the source code for running AlphaGeometry available on GitHub at [google-deepmind/alphageometry](https://github.com/google-deepmind/alphageometry). However, the AlphaGeometry system as Google released, with the Language Model trained by Google, still requires a tremendous amount of computing power to run when solving problems. As Google's paper mentioned, in order to solve IMO level problems in about 1.5 hour, it needed 4 GPU V100 and up to 250 CPUs. These are not the kind of hardware casual users and hobbyists have access to.
|