Skip to content

Commit

Permalink
Release NeuralGCM 1.0.0
Browse files Browse the repository at this point in the history
PiperOrigin-RevId: 637001025
  • Loading branch information
shoyer authored and NeuralGCM authors committed May 24, 2024
1 parent 2658bc1 commit d9d188a
Show file tree
Hide file tree
Showing 5 changed files with 12 additions and 13 deletions.
2 changes: 1 addition & 1 deletion docs/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ for reproducing and extending results from our paper,
archived re-forecasts for 2020, can be found in the
[WeatherBench2](https://github.com/google-research/weatherbench2) project.

The documentation here focuses mostly on our API for **inference** (i.e., running
The documentation here focuses mostly on our API for *inference* (i.e., running
trained NeuralGCM atmospheric models), which we believe is the most immediately
useful part of the NeuralGCM code for third parties. It is also a part of our
code that we can commit to supporting in roughly its current form.
Expand Down
8 changes: 5 additions & 3 deletions docs/inference_demo.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,8 @@
}
],
"source": [
"# if necessary, install NeuralGCM from source\n",
"! pip install -q -U gcsfs git+https://github.com/google-research/neuralgcm"
"# if necessary, install NeuralGCM and dependencies\n",
"! pip install -q -U neuralgcm dinosaur-dycore gcsfs"
]
},
{
Expand Down Expand Up @@ -245,7 +245,9 @@
"id": "W7lhecHtbo82"
},
"source": [
"## Compare forecast to ERA5"
"## Compare forecast to ERA5\n",
"\n",
"See [WeatherBench2](https://sites.research.google/weatherbench/) for more comprehensive evaluations and archived NeuralGCM forecasts."
]
},
{
Expand Down
9 changes: 3 additions & 6 deletions docs/installation.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,8 @@ For best performance, we recommend running NeuralGCM models on a computer with
an attached GPU or TPU. Otherwise, performance will be very slow.

You can install NeuralGCM from source using pip, which should automatically
install its dependencies, including [JAX](https://github.com/google/jax):
install its dependencies, including [JAX](https://github.com/google/jax) and
[Dinosaur](https://github.com/google-research/dinosaur):
```
pip install git+https://github.com/google-research/neuralgcm
pip install neuralgcm
```

Note that NeuralGCM requires the development version of
[Dinosaur](https://github.com/google-research/dinosaur), so if you update
NeuralGCM you will probably need to update Dinosaur, too.
2 changes: 1 addition & 1 deletion neuralgcm/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -44,4 +44,4 @@

from neuralgcm.api import PressureLevelModel

__version__ = "0.1.0"
__version__ = "1.0.0"
4 changes: 2 additions & 2 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -7,15 +7,15 @@ build-backend = "setuptools.build_meta"

[project]
name = "neuralgcm"
version = "0.1.0"
version = "1.0.0"
authors = [
{name = "Google LLC", email = "noreply@google.com"},
]
readme = "README.md"
license = {file = "LICENSE"}
requires-python = ">=3.10"
dependencies = [
"dinosaur@git+https://github.com/google-research/dinosaur",
"dinosaur-dycore",
"dm-haiku",
"gin-config",
"jax",
Expand Down

0 comments on commit d9d188a

Please sign in to comment.