diff --git a/README.md b/README.md
index 360e4bf..980839a 100644
--- a/README.md
+++ b/README.md
@@ -136,6 +136,11 @@ pip3 uninstall -y torch
 pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu121  # cu121 means cuda 12.1
 ```
 
+Now you are done with installing, try to modify one of the examples and run the below command!
+
+```
+python -m example.retrieval_qa.retrieval_qa_huggingface_demo
+```
 
 ### Frontend Dev Setup
 ```
@@ -148,7 +153,8 @@ npm run build
 If you are on EC2, you can launch a GPU instance with the following config:
 - EC2 `g5.2xlarge` (if you want to run a pretrained LLM with 7B parameters)
 - Deep Learning AMI PyTorch GPU 2.0.1 (Ubuntu 20.04)
-    <img src="example/image/readme_ec2_ami.jpg" alt="Alt text" width="50%" height="50%"/>
+    <img src="example/image/readme_ec2_ami.jpg" alt="Alt text" width="75%" height="75%"/>
 - EBS: at least 100G
+
     <img src="example/image/readme_ec2_storage.png" alt="Alt text" width="50%" height="50%"/>
 
diff --git a/docker/README.md b/docker/README.md
index 3f50217..54a9996 100644
--- a/docker/README.md
+++ b/docker/README.md
@@ -125,6 +125,8 @@ For example, here is a command to run `cambioml\pykoi` version `0.1_ec2_linux`.
 docker run -d -e RETRIEVAL_MODEL=mistralai/Mistral-7B-v0.1 -p 5000:5000 --gpus all --name pykoi_test cambioml/pykoi:0.1_ec2_linux
 ```
 
+***Note: this command may take a few minutes*** since it's loading a LLM.
+
 If you are running it in the background, with a `-d` tag, you can check the logs using the following command:
 ```
 docker logs [CONTAINER_NAME]