Merge branch 'main' of https://huggingface.co/ecmwf/aifs-single

README.md

@@ -1,5 +1,5 @@
 ---
-license: cc-by-sa-4.0
+license: cc-by-4.0
 metrics:
 - mse
 pipeline_tag: graph-ml
@@ -41,7 +41,8 @@ and direct observational data.
 
 - **Developed by:** ECMWF
 - **Model type:** Encoder-processor-decoder model
-- **License:** CC BY-SA 4.0
+- **License:** These model weights are published under a Creative Commons Attribution 4.0 International (CC BY 4.0).
+To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/
 
 ### Model Sources
 
@@ -57,22 +58,24 @@ and direct observational data.
 To generate a new forecast using AIFS, you can use [anemoi-inference](https://github.com/ecmwf/anemoi-inference). In the [following notebook](run_AIFS_v0_2_1.ipynb), a 
 step-by-step workflow is specified to run the AIFS using the HuggingFace model:
 
-- Install the required packages
-- Select a date
-- Get the data from the [ECMWF Open Data API](https://www.ecmwf.int/en/forecasts/datasets/open-data)
-- Get input fields
-- Add the single levels fields and pressure levels fields
-- Convert geopotential height into greopotential
-- Create the initial state
-- Create a runner
-- Run the forecast
-- Plot a field
+1. **Install Required Packages and Imports**
+2. **Retrieve Initial Conditions from ECMWF Open Data**
+  - Select a date
+  - Get the data from the [ECMWF Open Data API](https://www.ecmwf.int/en/forecasts/datasets/open-data)
+  - Get input fields
+  - Add the single levels fields and pressure levels fields
+  - Convert geopotential height into greopotential
+  - Create the initial state
+3. **Load the Model and Run the Forecast** 
+  - Download the Model's Checkpoint from Hugging Face
+  - Create a runner
+  - Run the forecast using anemoi-inference
+4. **Inspect the generated forecast**
+  - Plot a field
 
 
 🚨  **Note** we train AIFS using `flash_attention` (https://github.com/Dao-AILab/flash-attention).
-There are currently some issues when trying to install flash attention with the latest PyTorch version 2.5 and CUDA 12.4 (https://github.com/Dao-AILab/flash-attention/issues/1330).
-For that reason, we recommend you install PyTorch 2.4. 
-Additonally the use of 'Flash Attention' package also imposes certain requirements in terms of software and hardware. Those can be found under #Installation and Features in https://github.com/Dao-AILab/flash-attention
+The use of 'Flash Attention' package also imposes certain requirements in terms of software and hardware. Those can be found under #Installation and Features in https://github.com/Dao-AILab/flash-attention
 
 🚨 **Note** the `aifs_single_v0.2.1.ckpt` checkpoint just contains the model’s weights. 
 That file does not contain any information about the optimizer states, lr-scheduler states, etc.