fix broken link and move images into new folder

Author: msakande

articles/machine-learning/concept-online-deployment-model-specification.md

@@ -29,7 +29,7 @@ In Azure Machine Learning, after you create your deployment, the environment var
 
 We use the following local folder structure to illustrate how you can specify models that are available locally on your machine in an online deployment.
 
-:::image type="content" source="media/how-to-deploy-online-endpoints/multi-models-1.png" alt-text="A screenshot showing a local folder structure containing multiple models." lightbox="media/how-to-deploy-online-endpoints/multi-models-1.png":::
+:::image type="content" source="media/concept-online-deployment-model-specification/multi-models-1.png" alt-text="A screenshot showing a local folder structure containing multiple models." lightbox="media/concept-online-deployment-model-specification/multi-models-1.png":::
 
 ### Deployment configuration with a single local model
 
@@ -87,7 +87,7 @@ After you create your deployment, the environment variable `AZUREML_MODEL_DIR` p
 
 For this example, the contents of the `AZUREML_MODEL_DIR` folder look like this:
 
-:::image type="content" source="media/how-to-deploy-online-endpoints/multi-models-2.png" alt-text="A screenshot showing the folder structure of the storage location for multiple models." lightbox="media/how-to-deploy-online-endpoints/multi-models-2.png":::
+:::image type="content" source="media/concept-online-deployment-model-specification/multi-models-2.png" alt-text="A screenshot showing the folder structure of the storage location for multiple models." lightbox="media/concept-online-deployment-model-specification/multi-models-2.png":::
 
 Within your scoring script (`score.py`), you can load your models in the `init()` function. The following code loads the `sample_m1.pkl` model:
 
@@ -123,11 +123,11 @@ instance_count: 1
 
 For this example, consider that `local-multimodel:3` contains the following model artifacts, which can be viewed from the **Models** tab in the Azure Machine Learning studio:
 
-:::image type="content" source="media/how-to-deploy-online-endpoints/multi-models-3.png" alt-text="A screenshot of a folder structure showing the model artifacts of  a registered model." lightbox="media/how-to-deploy-online-endpoints/multi-models-3.png":::
+:::image type="content" source="media/concept-online-deployment-model-specification/multi-models-3.png" alt-text="A screenshot of a folder structure showing the model artifacts of  a registered model." lightbox="media/concept-online-deployment-model-specification/multi-models-3.png":::
 
 After you create your deployment, the environment variable `AZUREML_MODEL_DIR` points to the storage location within Azure where your models are stored. For example, `/var/azureml-app/azureml-models/local-multimodel/3` contains the models and the file structure. `AZUREML_MODEL_DIR` points to the folder containing the root of the model artifacts. Based on this example, the contents of the `AZUREML_MODEL_DIR` folder look like this:
 
-:::image type="content" source="media/how-to-deploy-online-endpoints/multi-models-4.png" alt-text="A screenshot of the folder structure showing multiple models." lightbox="media/how-to-deploy-online-endpoints/multi-models-4.png":::
+:::image type="content" source="media/concept-online-deployment-model-specification/multi-models-4.png" alt-text="A screenshot of the folder structure showing multiple models." lightbox="media/concept-online-deployment-model-specification/multi-models-4.png":::
 
 Within your scoring script (`score.py`), you can load your models in the `init()` function. For example, load the `diabetes.sav` model:
 

articles/machine-learning/media/how-to-deploy-online-endpoints/multi-models-1.png renamed to articles/machine-learning/media/concept-online-deployment-model-specification/multi-models-1.png

@@ -30,7 +30,7 @@ The following table shows the virtual machine (VM) stock keeping units (SKUs) th
 | X-Large       | Standard_D32a_v4 </br> Standard_D32as_v4 </br> Standard_D48a_v4 </br> Standard_D48as_v4 </br> Standard_D64a_v4 </br> Standard_D64as_v4 </br> Standard_D96a_v4 </br> Standard_D96as_v4 | Standard_F32s_v2 <br/> Standard_F48s_v2 <br/> Standard_F64s_v2 <br/> Standard_F72s_v2 <br/> Standard_FX24mds <br/> Standard_FX36mds <br/> Standard_FX48mds | Standard_E32s_v3 <br/> Standard_E48s_v3 <br/> Standard_E64s_v3 | Standard_NC48ads_A100_v4 </br> Standard_NC96ads_A100_v4 </br> Standard_ND96asr_v4 </br> Standard_ND96amsr_A100_v4 </br> Standard_ND40rs_v2 |
 
 > [!CAUTION]
-> `Standard_DS1_v2` and `Standard_F2s_v2` may be too small for bigger models and may lead to container termination due to insufficient memory, not enough space on the disk, or probe failure as it takes too long to initiate the container. If you face [OutOfQuota errors](how-to-troubleshoot-online-endpoints.md?tabs=cli#error-outofquota) or [ReourceNotReady errors](how-to-troubleshoot-online-endpoints.md?tabs=cli#error-resourcenotready), try bigger VM SKUs. If you want to reduce the cost of deploying multiple models with managed online endpoint, see [the example for multi models](concept-endpoints-online.md#use-multiple-local-models-in-a-deployment). 
+> `Standard_DS1_v2` and `Standard_F2s_v2` may be too small for bigger models and may lead to container termination due to insufficient memory, not enough space on the disk, or probe failure as it takes too long to initiate the container. If you face [OutOfQuota errors](how-to-troubleshoot-online-endpoints.md?tabs=cli#error-outofquota) or [ReourceNotReady errors](how-to-troubleshoot-online-endpoints.md?tabs=cli#error-resourcenotready), try bigger VM SKUs. If you want to reduce the cost of deploying multiple models with managed online endpoint, see [Deployment configuration with several local models](concept-online-deployment-model-specification.md#deployment-configuration-with-several-local-models).
 
 > [!NOTE]
 > We recommend having more than 3 instances for deployments in production scenarios. In addition, Azure Machine Learning reserves 20% of your compute resources for performing upgrades on some VM SKUs as described in [Virtual machine quota allocation for deployment](how-to-manage-quotas.md#virtual-machine-quota-allocation-for-deployment). VM SKUs that are exempted from this extra quota reservation are listed below: