Update readme (#23)

* Link to HF collection, add logo

* Add data URLs

* Update installation docs

README.md

@@ -1,30 +1,37 @@
 [![Docs](https://readthedocs.org/projects/ai2-climate-emulator/badge/?version=latest)](https://ai2-climate-emulator.readthedocs.io/en/latest/)
 [![PyPI](https://img.shields.io/pypi/v/fme.svg)](https://pypi.org/project/fme/)
 
-# ACE: Ai2 Climate Emulator
+<img src="ACE-logo.png" alt="Logo for the ACE Project" style="width: auto; height: 50px;">
+
+# Ai2 Climate Emulator
 This repo contains code accompanying "ACE: A fast, skillful learned global atmospheric model for climate prediction" ([arxiv:2310.02074](https://arxiv.org/abs/2310.02074)) and "Application of the Ai2 Climate Emulator to E3SMv2's global atmosphere model, with a focus on precipitation fidelity" ([JGR-ML](https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2024JH000136)).
 
-## Documentation
+## Installation
 
-See complete documentation [here](https://ai2-climate-emulator.readthedocs.io/en/latest/).
+```
+pip install fme
+```
 
-## Quickstart
+## Documentation
 
-A quickstart guide may be found [here](https://ai2-climate-emulator.readthedocs.io/en/latest/quickstart.html).
+See complete documentation [here](https://ai2-climate-emulator.readthedocs.io/en/latest/) and a quickstart guide [here](https://ai2-climate-emulator.readthedocs.io/en/latest/quickstart.html).
 
 ## Model checkpoints
 
-The trained ACE checkpoint and a 1-year subsample of the validation dataset used in [arxiv:2310.02074](https://arxiv.org/abs/2310.02074) are available in
-[this Zenodo repository](https://doi.org/10.5281/zenodo.10791087).
-The checkpoint trained on the [E3SMv2](https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2024JH000136) model
-and the corresponding dataset are available [here](https://portal.nersc.gov/archive/home/projects/e3sm/www/e3smv2-fme-dataset).
+Pretrained model checkpoints are available in the [ACE Hugging Face](https://huggingface.co/collections/allenai/ace-67327d822f0f0d8e0e5e6ca4) collection.
 
 ## Available datasets
 Two versions of the complete dataset described in [arxiv:2310.02074](https://arxiv.org/abs/2310.02074)
-are available on a requester pays Google Cloud Storage bucket:
+are available on a [requester pays](https://cloud.google.com/storage/docs/requester-pays) Google Cloud Storage bucket:
 ```
 gs://ai2cm-public-requester-pays/2023-11-29-ai2-climate-emulator-v1/data/repeating-climSST-1deg-zarrs
 gs://ai2cm-public-requester-pays/2023-11-29-ai2-climate-emulator-v1/data/repeating-climSST-1deg-netCDFs
 ```
 The `zarr` format is convenient for ad-hoc analysis. The netCDF version contains our
 train/validation split which was used for training and inference.
+
+The datasets used in the forthcoming ACE2 paper are available at:
+```
+gs://ai2cm-public-requester-pays/2024-11-13-ai2-climate-emulator-v2-amip/data/c96-1deg-shield/
+gs://ai2cm-public-requester-pays/2024-11-13-ai2-climate-emulator-v2-amip/data/era5-1deg-1940-2022.zarr/
+```

fme/docs/installation.rst

@@ -6,21 +6,23 @@ Installation
 
 All commands here are run from the top-level directory of the repository, unless otherwise stated.
 
-Experimental release
---------------------
+This is unsupported, pre-alpha software: use at your own risk! We are actively developing this software
+and will be making breaking changes to the API.
 
-There is no stable release. This is unsupported, pre-alpha software: use at your own risk!
+PyPI
+----
 
-To install directly from github, you can run:
+To install the latest release directly from PyPI, use:
 
 .. code-block:: shell
 
-    pip install git+https://github.com/ai2cm/ace#subdirectory=fme
+    pip install fme
 
 Conda
 -----
 
-To install with Conda, you must retrieve the sources from github:
+For convenience, we provide an easy way to create a conda environment with `fme` installed.
+First, clone the repository:
 
 .. code-block:: shell
 
@@ -41,7 +43,7 @@ This will create an environment named ``fme``, and should use the same package v
 Development
 -----------
 
-The package is not yet available on PyPI. Before installing, you must retrieve the sources from github:
+To install directly from source for development, clone the repository:
 
 .. code-block:: shell