diff --git a/docs/cluster-management/install.md b/docs/cluster-management/install.md
index 0525b52368..19eb6673e2 100644
--- a/docs/cluster-management/install.md
+++ b/docs/cluster-management/install.md
@@ -19,13 +19,16 @@ See [here](../miscellaneous/cli.md#install-cortex-cli-without-python-client) to
 ```bash
 # clone the Cortex repository
 git clone -b master https://github.com/cortexlabs/cortex.git
+
+# navigate to the Pytorch text generator example
+cd cortex/examples/pytorch/text-generator
 ```
 
 ### Using the CLI
 
 ```bash
 # deploy the model as a realtime api
-cortex deploy cortex/examples/pytorch/text-generator/cortex.yaml
+cortex deploy
 
 # view the status of the api
 cortex get --watch
@@ -39,7 +42,7 @@ cortex get text-generator
 # generate text
 curl <API endpoint> \
   -X POST -H "Content-Type: application/json" \
-  -d '{"text": "machine learning is"}' \
+  -d '{"text": "machine learning is"}'
 
 # delete the api
 cortex delete text-generator
@@ -54,7 +57,7 @@ import requests
 local_client = cortex.client("local")
 
 # deploy the model as a realtime api and wait for it to become active
-deployments = local_client.deploy("cortex/examples/pytorch/text-generator/cortex.yaml", wait=True)
+deployments = local_client.deploy("./cortex.yaml", wait=True)
 
 # get the api's endpoint
 url = deployments[0]["api"]["endpoint"]
diff --git a/pkg/workloads/cortex/client/README.md b/pkg/workloads/cortex/client/README.md
index d54fe029d5..38eb3abac4 100644
--- a/pkg/workloads/cortex/client/README.md
+++ b/pkg/workloads/cortex/client/README.md
@@ -38,6 +38,9 @@ You must have [Docker](https://docs.docker.com/install) installed to run Cortex
 ```bash
 # clone the Cortex repository
 git clone -b master https://github.com/cortexlabs/cortex.git
+
+# navigate to the Pytorch text generator example
+cd cortex/examples/pytorch/text-generator
 ```
 
 ### In Python
@@ -48,7 +51,7 @@ import requests
 local_client = cortex.client("local")
 
 # deploy the model as a realtime api and wait for it to become active
-deployments = local_client.deploy("cortex/examples/pytorch/text-generator/cortex.yaml", wait=True)
+deployments = local_client.deploy("./cortex.yaml", wait=True)
 
 # get the api's endpoint
 url = deployments[0]["api"]["endpoint"]
@@ -63,7 +66,7 @@ local_client.delete_api("text-generator")
 ### Using the CLI
 ```bash
 # deploy the model as a realtime api
-cortex deploy cortex/examples/pytorch/text-generator/cortex.yaml
+cortex deploy
 
 # view the status of the api
 cortex get --watch
@@ -77,7 +80,7 @@ cortex get text-generator
 # generate text
 curl <API endpoint> \
   -X POST -H "Content-Type: application/json" \
-  -d '{"text": "machine learning is"}' \
+  -d '{"text": "machine learning is"}'
 
 # delete the api
 cortex delete text-generator
diff --git a/pkg/workloads/cortex/client/cortex/binary/__init__.py b/pkg/workloads/cortex/client/cortex/binary/__init__.py
index 0c0b8541f6..f7cf580015 100644
--- a/pkg/workloads/cortex/client/cortex/binary/__init__.py
+++ b/pkg/workloads/cortex/client/cortex/binary/__init__.py
@@ -87,6 +87,7 @@ def run_cli(
         if not hide_output:
             if (not mixed_output) or (mixed_output and not result_found):
                 sys.stdout.write(c)
+                sys.stdout.flush()
 
     process.wait()