Merge pull request #283606 from MicrosoftDocs/main

8/5/2024 AM Publish

Author: Taojunshen

articles/ai-services/openai/concepts/models.md

@@ -276,8 +276,9 @@ These models can only be used with Embedding API requests.
 | `gpt-35-turbo` (1106) | East US2 <br> North Central US <br> Sweden Central <br> Switzerland West | Input: 16,385<br> Output: 4,096 |  Sep 2021|
 | `gpt-35-turbo` (0125)  | East US2 <br> North Central US <br> Sweden Central <br> Switzerland West | 16,385 | Sep 2021 |
 | `gpt-4` (0613) <sup>**1**</sup> | North Central US <br> Sweden Central | 8192 | Sep 2021 |
+| `gpt-4o-mini` <sup>**1**</sup> (2024-07-18) | North Central US <br> Sweden Central | Input: 128,000 <br> Output: 16,384  <br> Training example context length: 64,536 | Oct 2023 |
 
-**<sup>1</sup>** GPT-4 fine-tuning is currently in public preview. See our [GPT-4 fine-tuning safety evaluation guidance](/azure/ai-services/openai/how-to/fine-tuning?tabs=turbo%2Cpython-new&pivots=programming-language-python#safety-evaluation-gpt-4-fine-tuning---public-preview) for more information.
+**<sup>1</sup>** GPT-4 and GPT-4o mini fine-tuning is currently in public preview. See our [GPT-4 & GPT-4o mini fine-tuning safety evaluation guidance](/azure/ai-services/openai/how-to/fine-tuning?tabs=turbo%2Cpython-new&pivots=programming-language-python#safety-evaluation-gpt-4-fine-tuning---public-preview) for more information.
 
 ### Whisper models
 

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

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: build-2023, build-2023-dataai, devx-track-python
 ms.topic: how-to
-ms.date: 07/25/2024
+ms.date: 08/02/2024
 author: mrbullwinkle
 ms.author: mbullwin
 zone_pivot_groups: openai-fine-tuning-new

articles/ai-services/openai/includes/fine-tuning-openai-in-ai-studio.md

@@ -31,7 +31,8 @@ The following models support fine-tuning:
 - `gpt-35-turbo` (0613)
 - `gpt-35-turbo` (1106)
 - `gpt-35-turbo` (0125)
-- `gpt-4` (0613)**<sup>*</sup>** 
+- `gpt-4` (0613)**<sup>*</sup>**
+- `gpt-4o-mini` (2024-07-18)**<sup>*</sup>**
 
 **<sup>*</sup>** Fine-tuning for this model is currently in public preview.
 

articles/ai-services/openai/includes/fine-tuning-python.md

@@ -32,6 +32,7 @@ The following models support fine-tuning:
 - `gpt-35-turbo` (1106)
 - `gpt-35-turbo` (0125)
 - `gpt-4` (0613)**<sup>*</sup>**
+- `gpt-4o-mini` (2024-07-18)**<sup>*</sup>**
 
 **<sup>*</sup>** Fine-tuning for this model is currently in public preview.
 

articles/ai-services/openai/includes/fine-tuning-rest.md

@@ -6,7 +6,7 @@ description: Learn how to create your own customized model with Azure OpenAI Ser
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 05/16/2024
+ms.date: 08/02/2024
 author: mrbullwinkle
 ms.author: mbullwin
 ---
@@ -30,7 +30,8 @@ The following models support fine-tuning:
 - `gpt-35-turbo` (0613)
 - `gpt-35-turbo` (1106)
 - `gpt-35-turbo` (0125)
-- `gpt-4` (0613)**<sup>*</sup>** 
+- `gpt-4` (0613)**<sup>*</sup>**
+- `gpt-4o-mini` (2024-07-18)**<sup>*</sup>**
 
 **<sup>*</sup>** Fine-tuning for this model is currently in public preview.
 

articles/ai-services/openai/includes/fine-tuning-studio.md

@@ -29,7 +29,8 @@ The following models support fine-tuning:
 - `gpt-35-turbo` (0613)
 - `gpt-35-turbo` (1106)
 - `gpt-35-turbo` (0125)
-- `gpt-4` (0613)**<sup>*</sup>** 
+- `gpt-4` (0613)**<sup>*</sup>**
+- `gpt-4o-mini` (2024-07-18)**<sup>*</sup>**
 
 **<sup>*</sup>** Fine-tuning for this model is currently in public preview.
 

articles/ai-services/openai/includes/safety-evaluation.md

@@ -10,13 +10,13 @@ author: mrbullwinkle
 ms.author: mbullwin
 ---
 
-GPT-4 is our most advanced model that can be fine-tuned to your needs. As with Azure OpenAI models generally, the advanced capabilities of fine-tuned models come with increased responsible AI challenges related to harmful content, manipulation, human-like behavior, privacy issues, and more. Learn more about risks, capabilities, and limitations in the [Overview of Responsible AI practices](/legal/cognitive-services/openai/overview?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext) and [Transparency Note](/legal/cognitive-services/openai/transparency-note?context=%2Fazure%2Fcognitive-services%2Fopenai%2Fcontext%2Fcontext&tabs=text). To help mitigate the risks associated with GPT-4 fine-tuned models, we have implemented additional evaluation steps to help detect and prevent harmful content in the training and outputs of fine-tuned models. These steps are grounded in the [Microsoft Responsible AI Standard](https://www.microsoft.com/ai/responsible-ai) and [Azure OpenAI Service content filtering](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new).
+GPT-4 and GPT-4o-mini are our most advanced models that can be fine-tuned to your needs. As with Azure OpenAI models generally, the advanced capabilities of fine-tuned models come with increased responsible AI challenges related to harmful content, manipulation, human-like behavior, privacy issues, and more. Learn more about risks, capabilities, and limitations in the [Overview of Responsible AI practices](/legal/cognitive-services/openai/overview?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext) and [Transparency Note](/legal/cognitive-services/openai/transparency-note?context=%2Fazure%2Fcognitive-services%2Fopenai%2Fcontext%2Fcontext&tabs=text). To help mitigate the risks associated with GPT-4 and GPT-4o-mini fine-tuned models, we have implemented additional evaluation steps to help detect and prevent harmful content in the training and outputs of fine-tuned models. These steps are grounded in the [Microsoft Responsible AI Standard](https://www.microsoft.com/ai/responsible-ai) and [Azure OpenAI Service content filtering](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new).
 
 - Evaluations are conducted in dedicated, customer specific, private workspaces;
 - Evaluation endpoints are in the same geography as the Azure OpenAI resource;
 - Training data is not stored in connection with performing evaluations; only the final model assessment (deployable or not deployable) is persisted; and
 
-GPT-4 fine-tuned model evaluation filters are set to predefined thresholds and cannot be modified by customers; they aren't tied to any custom content filtering configuration you may have created.
+GPT-4 and GPT-4o-mini fine-tuned model evaluation filters are set to predefined thresholds and cannot be modified by customers; they aren't tied to any custom content filtering configuration you may have created.
 
 ### Data evaluation
 

articles/ai-services/openai/whats-new.md

@@ -10,7 +10,7 @@ ms.custom:
   - ignite-2023
   - references_regions
 ms.topic: whats-new
-ms.date: 07/31/2024
+ms.date: 08/02/2024
 recommendations: false
 ---
 
@@ -20,6 +20,10 @@ This article provides a summary of the latest releases and major documentation u
 
 ## July 2024
 
+### GPT-4o mini is now available for fine-tuning
+
+GPT-4o mini fine-tuning is [now available in public preview](./concepts/models.md#fine-tuning-models) in Sweden Central and in North Central US.
+
 ### Assistants File Search tool is now billed
 
 The [file search](./how-to/file-search.md) tool for Assistants now has additional charges for usage. See the [pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) for more information.

articles/ai-studio/how-to/deploy-models-serverless-availability.md

@@ -1,7 +1,7 @@
 ---
 title: Region availability for models in Serverless API endpoints
 titleSuffix: Azure AI Studio
-description: Learn about the regions where each model is available for deployment in serverless API endpoints.
+description: Learn about the regions where each model is available for deployment in serverless API endpoints via Azure AI Studio.
 manager: scottpolly
 ms.service: azure-ai-studio
 ms.topic: how-to
@@ -16,7 +16,7 @@ ms.custom:
  - references_regions
 ---
 
-# Region availability for models in serverless API endpoints | Azure AI Studio
+# Region availability for models in serverless API endpoints
 
 In this article, you learn about which regions are available for each of the models supporting serverless API endpoint deployments.
 

articles/application-gateway/application-gateway-diagnostics.md

@@ -48,7 +48,7 @@ You have the following options to store the logs in your preferred location.
   * [AGWFirewallLogs](/azure/azure-monitor/reference/tables/agwfirewalllogs)
 
 > [!NOTE]
-> The resource specific option is currently available in all **public regions**.<br>
+> The resource specific option is currently available in all **clouds**.<br>
 > Existing users can continue using Azure Diagnostics, or can opt for dedicated tables by switching the toggle in Diagnostic settings to **Resource specific**, or to **Dedicated** in API destination. Dual mode isn't possible. The data in all the logs can either flow to Azure Diagnostics, or to dedicated tables. However, you can have multiple diagnostic settings where one data flow is to azure diagnostic and another is using resource specific at the same time. 
 
  **Selecting the destination table in Log analytics :** All Azure services eventually use the resource-specific tables. As part of this transition, you can select Azure diagnostic or resource specific table in the diagnostic setting using a toggle button. The toggle is set to **Resource specific** by default and in this mode, logs for new selected categories are sent to dedicated tables in Log Analytics, while existing streams remain unchanged. See the following example.