anaprietonem
commited on
Commit
•
b8aa337
1
Parent(s):
1438f0d
Update README.md
Browse files
README.md
CHANGED
@@ -61,7 +61,6 @@ You can find an example of a set of initial conditions in the GRIB file `example
|
|
61 |
|
62 |
Use the code below to get started with the model.
|
63 |
|
64 |
-
|
65 |
```
|
66 |
# 1st - create the conda environment
|
67 |
export CONDA_ENV=aifs-env
|
@@ -86,6 +85,11 @@ Additonally the use of 'Flash Attention' package also imposes certain requiremen
|
|
86 |
🚨 **Note** the `aifs_single_v0.2.1.ckpt` checkpoint just contains the model’s weights.
|
87 |
That file does not contain any information about the optimizer states, lr-scheduler states, etc.
|
88 |
|
|
|
|
|
|
|
|
|
|
|
89 |
After running the `ai-models` command the output of the forecast should be written into `anemoi.grib`
|
90 |
Below you can find an example to read that file and load it as numpy array or xarray.
|
91 |
|
@@ -97,7 +101,7 @@ source_filename='anemoi.grib'
|
|
97 |
aifs_forecast = ekd.from_source('file',source_filename)
|
98 |
|
99 |
# to load it as a numpy array
|
100 |
-
aifs_forecast.to_numpy()
|
101 |
|
102 |
# to load it as a xarray array
|
103 |
aifs_forecast.to_xarray()
|
|
|
61 |
|
62 |
Use the code below to get started with the model.
|
63 |
|
|
|
64 |
```
|
65 |
# 1st - create the conda environment
|
66 |
export CONDA_ENV=aifs-env
|
|
|
85 |
🚨 **Note** the `aifs_single_v0.2.1.ckpt` checkpoint just contains the model’s weights.
|
86 |
That file does not contain any information about the optimizer states, lr-scheduler states, etc.
|
87 |
|
88 |
+
**Note** By default, when running `ai-models` the model will be run for a 10-day lead time (240 hours).
|
89 |
+
It is possible to extend or modify the lead time to for example 15 days by doing `ai-models --lead-time 360`
|
90 |
+
Please refer to `ai-models` documentation for more information regarding defaults and available command line options.
|
91 |
+
|
92 |
+
|
93 |
After running the `ai-models` command the output of the forecast should be written into `anemoi.grib`
|
94 |
Below you can find an example to read that file and load it as numpy array or xarray.
|
95 |
|
|
|
101 |
aifs_forecast = ekd.from_source('file',source_filename)
|
102 |
|
103 |
# to load it as a numpy array
|
104 |
+
aifs_forecast.to_numpy() #
|
105 |
|
106 |
# to load it as a xarray array
|
107 |
aifs_forecast.to_xarray()
|