update preview note for deepseek model

Author: msakande

articles/ai-studio/how-to/deploy-models-deepseek.md

@@ -21,6 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about DeepSeek-R1 and how to use them.
 DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks. It features 671B total parameters with 37B active parameters, and 128k context length.
 
+[!INCLUDE [models-preview](../includes/models-preview.md)]
 
 
 ::: zone pivot="programming-language-python"
@@ -240,7 +241,7 @@ print_stream(result)
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -507,7 +508,7 @@ for await (const event of sses) {
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -800,7 +801,7 @@ StreamMessageAsync(client).GetAwaiter().GetResult();
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -1086,7 +1087,7 @@ The last message in the stream has `finish_reason` set, indicating the reason fo
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.