fix numbering

content/modules/ROOT/pages/02-vllm.adoc

@@ -17,21 +17,24 @@ Treating the model as an OCI artifact allows us to easily promote the model betw
 
 Since we are using a ModelCar container to deploy our model instead of S3, we will need to deploy the resources without the OpenShift AI Dashboard.
 
-1. To start, With the `redhat-ods-applications` namespace selected, navigate to Developer perspective in the OpenShift Web Console.  From the `+Add` page, select `All Services`.
+. To start, With the `redhat-ods-applications` namespace selected, navigate to Developer perspective in the OpenShift Web Console.  From the `+Add` page, select `All Services`.
 
 image::02-add-catalog.png[Add Catalog]
 
-2. Search for `vLLM` and select the `vLLM ServingRuntime for KServe` template
+[start=2]
+. Search for `vLLM` and select the `vLLM ServingRuntime for KServe` template
 
 image::02-select-template.png[Select Template]
 
-3. Choose to `Instantiate Template`.  Select the `composer-ai-apps` project and click `Create`
+[start=3]
+. Choose to `Instantiate Template`.  Select the `composer-ai-apps` project and click `Create`
 
 image::02-instantiate-template.png[Instantiate Template]
 
 The vLLM ServingRuntime for KServe `Template` is the same template that the OpenShift AI Dashboard uses when deploying a new instance.  Unlike the Dashboard though, the template with just create the `ServingRuntime` object and not the `InferenceService`.
 
-4. Next we will need to create the InferenceService.  Click the `+` in the top right hand corner and paste the following object in and click `Create`.
+[start=4]
+. Next we will need to create the InferenceService.  Click the `+` in the top right hand corner and paste the following object in and click `Create`.
 
 [source,yaml]
 ----