phi-3 vision AzureML

Author: msakande

articles/machine-learning/how-to-deploy-models-phi-3-vision.md.md renamed to articles/machine-learning/how-to-deploy-models-phi-3-vision.md

@@ -5,7 +5,7 @@ description: Learn how to use Phi-3 chat model with vision with Azure AI Studio.
 ms.service: azure-ai-studio
 manager: scottpolly
 ms.topic: how-to
-ms.date: 08/16/2024
+ms.date: 08/19/2024
 ms.reviewer: kritifaujdar
 reviewer: fkriti
 ms.author: mopeakande
@@ -143,7 +143,7 @@ response = client.complete(
 ```
 
 > [!NOTE]
-> Phi-3-vision-128k-Instruct don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-3-vision-128k-Instruct doesn't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -463,7 +463,7 @@ var response = await client.path("/chat/completions").post({
 ```
 
 > [!NOTE]
-> Phi-3-vision-128k-Instruct don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-3-vision-128k-Instruct doesn't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -820,7 +820,7 @@ Response<ChatCompletions> response = client.Complete(requestOptions);
 ```
 
 > [!NOTE]
-> Phi-3-vision-128k-Instruct don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-3-vision-128k-Instruct doesn't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -1115,7 +1115,7 @@ The following example shows how you can create a basic chat completions request
 ```
 
 > [!NOTE]
-> Phi-3-vision-128k-Instruct don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-3-vision-128k-Instruct doesn't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 

articles/machine-learning/toc.yml

@@ -598,6 +598,8 @@
       items:
         - name: Phi-3 family chat models
           href: how-to-deploy-models-phi-3.md
+        - name: Phi-3 chat model with vision
+          href: how-to-deploy-models-phi-3-vision.md
     - name: How to deploy TimeGEN-1 model
       href: how-to-deploy-models-timegen-1.md
     - name: How to deploy Mistral family models