Merge pull request #249411 from GitHubber17/141588-refresh-5

Azure OpenAI Freshness Pass - User Story: 141588

Author: v-dirichards

articles/ai-services/openai/how-to/fine-tuning.md

@@ -1,31 +1,31 @@
 ---
-title: 'How to customize a model with Azure OpenAI Service'
+title: 'Customize a model with Azure OpenAI Service'
 titleSuffix: Azure OpenAI
-description: Learn how to create your own customized model with Azure OpenAI
+description: Learn how to create your own customized model with Azure OpenAI Service by using Python, the REST APIs, or Azure OpenAI Studio.
 services: cognitive-services
 manager: nitinme
 ms.service: cognitive-services
 ms.subservice: openai
 ms.custom: build-2023, build-2023-dataai, devx-track-python
 ms.topic: how-to
-ms.date: 04/05/2023
+ms.date: 09/01/2023
 author: ChrisHMSFT
 ms.author: chrhoder
 zone_pivot_groups: openai-fine-tuning
 keywords: 
 ---
-# Learn how to customize a model for your application
 
-Azure OpenAI Service lets you tailor our models to your personal datasets using a process known as *fine-tuning*. This customization step will let you get more out of the service by providing:
+# Customize a model with Azure OpenAI Service
 
-- Higher quality results than what you can get just from prompt design
-- The ability to train on more examples than can fit into a prompt
-- Lower-latency requests
+Azure OpenAI Service lets you tailor our models to your personal datasets by using a process known as *fine-tuning*. This customization step lets you get more out of the service by providing:
+
+- Higher quality results than what you can get just from prompt design.
+- The ability to train on more examples than can fit into a prompt.
+- Lower-latency requests.
 
 A customized model improves on the few-shot learning approach by training the model's weights on your specific prompts and structure. The customized model lets you achieve better results on a wider number of tasks without needing to provide examples in your prompt. The result is less text sent and fewer tokens processed on every API call, saving cost and improving request latency.
 
-> [!NOTE]
-> There is a breaking change in the `create` fine tunes command in the latest 12-01-2022 GA API. For the latest command syntax consult the [reference documentation](/rest/api/cognitiveservices/azureopenaistable/fine-tunes/create)
+
 
 ::: zone pivot="programming-language-studio"
 

articles/ai-services/openai/includes/fine-tune.md

@@ -1,18 +1,25 @@
 ---
 title: Fine-tuning inactivity guidance
 titleSuffix: Azure OpenAI
-description: Fine-tuning inactivity guidance
+description: Describes the fine-tuning guidance for a model deployment that's inactive for more than 15 days.
 author: mrbullwinkle 
 ms.author: mbullwin 
 ms.service: cognitive-services
 ms.topic: include
-ms.date: 04/05/2023
+ms.date: 09/01/2023
 manager: nitinme
 keywords: ChatGPT
 
 ---
 
 > [!IMPORTANT]
-> After you deploy a customized model, if at any time the deployment remains inactive for greater than fifteen (15) days, the deployment is deleted. The deployment of a customized model is *inactive* if the model was deployed more than fifteen (15) days ago and no completions or chat completions calls were made to it during a continuous 15-day period.
+> After you deploy a customized model, if at any time the deployment remains inactive for greater than fifteen (15) days,
+> the deployment is deleted. The deployment of a customized model is _inactive_ if the model was deployed more than fifteen (15) days ago
+> and no completions or chat completions calls were made to it during a continuous 15-day period.
 >
->The deletion of an inactive deployment doesn't delete or affect the underlying customized model, and the customized model can be redeployed at any time. As described in [Azure OpenAI Service pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/), each customized (fine-tuned) model that is deployed incurs an hourly hosting cost regardless of whether completions or chat completions calls are being made to the model. To learn more about planning and managing costs with Azure OpenAI, refer to our [cost management guide](../how-to/manage-costs.md#base-series-and-codex-series-fine-tuned-models).
+> The deletion of an inactive deployment doesn't delete or affect the underlying customized model,
+> and the customized model can be redeployed at any time.
+> As described in [Azure OpenAI Service pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/),
+> each customized (fine-tuned) model that's deployed incurs an hourly hosting cost regardless of whether completions
+> or chat completions calls are being made to the model. To learn more about planning and managing costs with Azure OpenAI,
+> refer to the guidance in [Plan to manage costs for Azure OpenAI Service](../how-to/manage-costs.md#base-series-and-codex-series-fine-tuned-models).