diff --git a/README.md b/README.md
index 0b78e6a7..304d30cb 100644
--- a/README.md
+++ b/README.md
@@ -373,7 +373,7 @@ address_parser.retrain(
 
 ### Download Our Models
 
-Here are the URLs to download our pretrained models directly
+Deepparse handles model downloads when you use it, but you can also pre-download our model. Here are the URLs to download our pretrained models directly
 
 - [FastText](https://graal.ift.ulaval.ca/public/deepparse/fasttext.ckpt),
 - [FastTextAttention](https://graal.ift.ulaval.ca/public/deepparse/fasttext_attention.ckpt),
@@ -382,7 +382,7 @@ Here are the URLs to download our pretrained models directly
 - [FastText Light](https://graal.ift.ulaval.ca/public/deepparse/fasttext.magnitude.gz) (
   using [Magnitude Light](https://github.com/davebulaval/magnitude-light)).
 
-Or you can use our cli to download our pretrained models directly using:
+Or you can use our CLI to download our pretrained models directly using:
 
 ```sh
 download_model <model_name>
diff --git a/docs/source/get_started/get_started.rst b/docs/source/get_started/get_started.rst
index 9afccc8e..4b6e4971 100644
--- a/docs/source/get_started/get_started.rst
+++ b/docs/source/get_started/get_started.rst
@@ -132,14 +132,14 @@ a complete example.
 Download Our Models
 *******************
 
-Here are the URLs to download our pretrained models directly
+Deepparse handles model downloads when you use it, but you can also pre-download our model. Here are the URLs to download our pretrained models directly
     - `FastText <https://graal.ift.ulaval.ca/public/deepparse/fasttext.ckpt>`__,
     - `FastTextAttention <https://graal.ift.ulaval.ca/public/deepparse/fasttext_attention.ckpt>`__,
     - `BPEmb <https://graal.ift.ulaval.ca/public/deepparse/bpemb.ckpt>`__,
     - `BPEmbAttention <https://graal.ift.ulaval.ca/public/deepparse/bpemb_attention.ckpt>`__,
     - `FastText Light <https://graal.ift.ulaval.ca/public/deepparse/fasttext.magnitude.gz>`__ (using `Magnitude Light <https://github.com/davebulaval/magnitude-light>`__),.
 
-Or you can use our cli to download our pretrained models directly using:
+Or you can use our CLI to download our pretrained models directly using:
 
 .. code-block:: sh