Update articles/machine-learning/how-to-deploy-custom-container.md

Co-authored-by: SeokJin Han <[email protected]>

Author: dhanvia

articles/machine-learning/how-to-deploy-custom-container.md

@@ -340,7 +340,7 @@ You can optionally configure your `model_mount_path` value. By adjusting this se
 > The `model_mount_path` value must be a valid absolute path in Linux (in the guest OS of the container image).
 
 > [!IMPORTANT]
-> For BYOC scenarios, where a custom `model_mount_path` is to be configured on an online deployment, you must set the [`inference_config` parameter](#the-inference_config-parameter) in the custom environment created for the model, in order for the environment to be recognized as a custom environment. For such scenarios, use the Azure CLI or Python SDK to set the parameter. Do not try to set the parameter when creating the custom environment in the Azure portal, as there are some known limitations with configuring the `inference_config` parameter this way.
+> `model_mount_path` is usable only in BYOC (Bring your own container) scenario. In BYOC scenario, the environment that the online deployment uses must have [`inference_config` parameter](#the-inference_config-parameter) configured. You can use Azure ML CLI or Python SDK to specify `inference_config` parameter when creating the environment. Studio UI currently doesn't support specifying this parameter.
 
 When you change the value of `model_mount_path`, you also need to update the `MODEL_BASE_PATH` environment variable. Set `MODEL_BASE_PATH` to the same value as `model_mount_path` to avoid a failed deployment due to an error about the base path not being found.