Merge pull request #2772 from MicrosoftDocs/main

2/6/2025 AM Publish

Author: Taojunshen

articles/ai-services/immersive-reader/tutorial-ios-picture-immersive-reader.md

@@ -39,9 +39,9 @@ Choose **Single View App**.
 
 ## Get the SDK CocoaPod
 
-The easiest way to use the Immersive Reader SDK is via CocoaPods. To install via Cocoapods:
+The easiest way to use the Immersive Reader SDK is via CocoaPods. To install via CocoaPods:
 
-1. Follow the [guide to install Cocoapods](http://guides.cocoapods.org/using/getting-started.html).
+1. Follow the [guide to install CocoaPods](http://guides.cocoapods.org/using/getting-started.html).
 
 2. Create a Podfile by running `pod init` in your Xcode project's root directory.
 

articles/ai-services/openai/concepts/model-retirements.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the model deprecations and retirements in Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 01/15/2025
+ms.date: 02/06/2025
 ms.custom: 
 manager: nitinme
 author: mrbullwinkle
@@ -97,17 +97,19 @@ These models are currently available for use in Azure OpenAI Service.
 | `davinci-002` | 1 | Retirement Date: January 27, 2025 | |
 | `dall-e-2`| 2 | January 27, 2025 | `dalle-3` |
 | `dall-e-3` | 3 | No earlier than April 30, 2025 | |
-| `gpt-35-turbo` | 0301 | February 13, 2025<br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 13, 2025.   | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
-| `gpt-35-turbo`<br>`gpt-35-turbo-16k` | 0613 | February 13, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 13, 2025.  | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`|
-| `gpt-35-turbo` | 1106 | No earlier than March 31, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 13, 2025. | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini` |
+| `gpt-35-turbo` | 0301 | February 13, 2025<br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.   | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
+| `gpt-35-turbo`<br>`gpt-35-turbo-16k` | 0613 | February 13, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.  | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`|
+| `gpt-35-turbo` | 1106 | No earlier than March 31, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025. | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini` |
 | `gpt-35-turbo` | 0125 | No earlier than May 31, 2025 | `gpt-4o-mini` |
 | `gpt-4`<br>`gpt-4-32k` | 0314 | June 6, 2025 | `gpt-4o` |
 | `gpt-4`<br>`gpt-4-32k` | 0613 | June 6, 2025 | `gpt-4o` |
 | `gpt-4` | turbo-2024-04-09 | No earlier than April 9, 2025 | `gpt-4o`|
-| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than January 27, 2025 **<sup>1</sup>** | `gpt-4o`|
-| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than January 27, 2025 **<sup>1</sup>**  | `gpt-4o` |
-| `gpt-4` | vision-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than January 27, 2025  **<sup>1</sup>** | `gpt-4o`|
+| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: February 28, 2025  | `gpt-4o`|
+| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: February 28, 2025  | `gpt-4o` |
+| `gpt-4` | vision-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025  **<sup>1</sup>** <br>Retirement date: February 28, 2025 | `gpt-4o`|
 | `gpt-4o` | 2024-05-13 | No earlier than May 20, 2025 <br><br>Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `2024-08-06`, starting on February 13, 2025. | |
+| `gpt-4o` | 2024-08-06 | No earlier than August 6, 2025  | |
+| `gpt-4o` | 2024-11-20 | No earlier than November 20, 2025  | |
 | `gpt-4o-mini` | 2024-07-18 | No earlier than July 18, 2025  | |
 | `gpt-4o-realtime-preview` | 2024-10-01 | No earlier than September 30, 2025  | `gpt-4o-realtime-preview` (version 2024-12-17) or `gpt-4o-mini-realtime-preview` (version 2024-12-17) |
 | `gpt-3.5-turbo-instruct` | 0914 | No earlier than April 1, 2025 |  |
@@ -126,7 +128,7 @@ These models are currently available for use in Azure OpenAI Service.
 
 | Model | Current default version | New default version | Default upgrade date |
 |---|---|---|---|
-| `gpt-35-turbo` | 0301 | 0125 | Deployments of versions `0301`, `0613`, and `1106` set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 13, 2025.|
+| `gpt-35-turbo` | 0301 | 0125 | Deployments of versions `0301`, `0613`, and `1106` set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.|
 |  `gpt-4o` | 2024-05-13 | 2024-08-06 | Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `2024-08-06`, starting on February 13, 2025. |
 
 ## Deprecated models
@@ -167,6 +169,10 @@ If you're an existing customer looking for information about these models, see [
 
 ## Retirement and deprecation history
 
+## February 6, 2025
+
+- Updates to `gpt-35-turbo`, `gpt-4` preview models, and `gpt-4o` models.
+
 ## January 9, 2025
 
 - `o1` added.

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

@@ -320,7 +320,6 @@ These models can only be used with Embedding API requests.
 
 |  Model ID  | Max Request (characters) |
 |  --- | :---: |
-| dalle2 (preview)  | 1,000 |
 | dall-e-3  | 4,000 |
 
 # [Audio](#tab/standard-audio)

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

@@ -49,7 +49,7 @@ We use LoRA, or low rank approximation, to fine-tune models in a way that reduce
 Azure OpenAI fine-tuning supports [global standard deployments](./deployment-types.md#global-standard) in East US2, North Central US, and Sweden Central for:
 
 - `gpt-4o-mini-2024-07-18`
-- `gpt-4o-2024-08-06` (New deployments aren't available until January 2025)
+- `gpt-4o-2024-08-06`
 
 Global standard fine-tuned deployments offer [cost savings](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/), but custom model weights may temporarily be stored outside the geography of your Azure OpenAI resource.
 

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

@@ -6,7 +6,7 @@ author: mrbullwinkle
 ms.author: mbullwin 
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 10/31/2024
+ms.date: 02/06/2025
 manager: nitinme
 ---
 
@@ -17,8 +17,6 @@ manager: nitinme
 
 |  Model ID  | Fine-tuning regions | Max request (tokens) | Training Data (up to) |
 |  --- | --- | :---: | :---: |
-| `babbage-002` | North Central US <br> Sweden Central  <br> Switzerland West | 16,384 | Sep 2021 |
-| `davinci-002` | North Central US <br> Sweden Central  <br> Switzerland West | 16,384 | Sep 2021 |
 | `gpt-35-turbo` (0613) | East US2 <br> North Central US <br> Sweden Central <br> Switzerland West | 4,096 | Sep 2021 |
 | `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 |

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

@@ -28,8 +28,6 @@ ms.custom: include, build-2024
 
 The following models support fine-tuning:
 
-- `babbage-002`
-- `davinci-002`
 - `gpt-35-turbo` (0613)
 - `gpt-35-turbo` (1106)
 - `gpt-35-turbo` (0125)
@@ -64,10 +62,6 @@ Take a moment to review the fine-tuning workflow for using Azure AI Foundry:
 
 Your training data and validation data sets consist of input and output examples for how you would like the model to perform.
 
-Different model types require a different format of training data.
-
-# [chat completion models](#tab/turbo)
-
 The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo-0613` the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
 
 If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-0613` model please refer to the [Azure OpenAI fine-tuning tutorial.](../tutorials/fine-tune.md)
@@ -104,54 +98,6 @@ The more training examples you have, the better. Fine tuning jobs will not proce
 
 In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data, without first pruning the dataset for only the highest quality examples you could end up with a model that performs much worse than expected.
 
-# [babbage-002/davinci-002](#tab/completionfinetuning)
-
-The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document in which each line represents a single prompt-completion pair. The OpenAI command-line interface (CLI) includes [a data preparation tool](#openai-cli-data-preparation-tool) that validates, gives suggestions, and reformats your training data into a JSONL file ready for fine-tuning.
-
-```json
-{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
-{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
-{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
-```
-
-In addition to the JSONL format, training and validation data files must be encoded in UTF-8 and include a byte-order mark (BOM). The file must be less than 512 MB in size.
-
-### Create your training and validation datasets
-
-Designing your prompts and completions for fine-tuning is different from designing your prompts for use with any of [our GPT-3 base models](../concepts/legacy-models.md#gpt-3-models). Prompts for completion calls often use either detailed instructions or few-shot learning techniques, and consist of multiple examples. For fine-tuning, each training example should consist of a single input prompt and its desired completion output. You don't need to give detailed instructions or multiple completion examples for the same prompt.
-
-The more training examples you have, the better. The minimum number of training examples is 10, but such a small number of examples is often not enough to noticeably influence model responses. OpenAI states it's best practice to have at least 50 high quality training examples. However, it is entirely possible to have a use case that might require 1,000's of high quality training examples to be successful.
-
-In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data, without first pruning the dataset for only the highest quality examples you could end up with a model that performs much worse than expected.
-
-### OpenAI CLI data preparation tool
-
-OpenAI's CLI data preparation tool was developed for the previous generation of fine-tuning models to assist with many of the data preparation steps. This tool will only work for data preparation for models that work with the completion API like `babbage-002` and `davinci-002`. The tool validates, gives suggestions, and reformats your data into a JSONL file ready for fine-tuning.
-
-To install the OpenAI CLI, run the following Python command:
-
-```console
-pip install openai==0.28.1
-```
-
-To analyze your training data with the data preparation tool, run the following Python command. Replace the _\<LOCAL_FILE>_ argument with the full path and file name of the training data file to analyze:
-
-```console
-openai tools fine_tunes.prepare_data -f <LOCAL_FILE>
-```
-
-This tool accepts files in the following data formats, if they contain a prompt and a completion column/key:
-
-- Comma-separated values (CSV)
-- Tab-separated values (TSV)
-- Microsoft Excel workbook (XLSX)
-- JavaScript Object Notation (JSON)
-- JSON Lines (JSONL)
-
-After it guides you through the process of implementing suggested changes, the tool reformats your training data and saves output into a JSONL file ready for fine-tuning.
-
----
-
 ## Create your fine-tuned model
 
 To fine-tune an Azure OpenAI model in an existing Azure AI Foundry project, follow these steps:

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

@@ -26,8 +26,6 @@ ms.author: mbullwin
 
 The following models support fine-tuning:
 
-- `babbage-002`
-- `davinci-002`
 - `gpt-35-turbo` (0613)
 - `gpt-35-turbo` (1106)
 - `gpt-35-turbo` (0125)
@@ -60,10 +58,6 @@ Take a moment to review the fine-tuning workflow for using the Python SDK with A
 
 Your training data and validation data sets consist of input and output examples for how you would like the model to perform.
 
-Different model types require a different format of training data.
-
-# [chat completion models](#tab/turbo)
-
 The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo-0613` the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
 
 If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-0613` please refer to the [Azure OpenAI fine-tuning tutorial](../tutorials/fine-tune.md)
@@ -100,54 +94,6 @@ The more training examples you have, the better. Fine tuning jobs will not proce
 
 In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data, without first pruning the dataset for only the highest quality examples you could end up with a model that performs much worse than expected.
 
-# [babbage-002/davinci-002](#tab/completionfinetuning)
-
-The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document in which each line represents a single prompt-completion pair. The OpenAI command-line interface (CLI) includes [a data preparation tool](#openai-cli-data-preparation-tool) that validates, gives suggestions, and reformats your training data into a JSONL file ready for fine-tuning.
-
-```json
-{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
-{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
-{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
-```
-
-In addition to the JSONL format, training and validation data files must be encoded in UTF-8 and include a byte-order mark (BOM). The file must be less than 512 MB in size.
-
-### Create your training and validation datasets
-
-Designing your prompts and completions for fine-tuning is different from designing your prompts for use with any of [our GPT-3 base models](../concepts/legacy-models.md#gpt-3-models). Prompts for completion calls often use either detailed instructions or few-shot learning techniques, and consist of multiple examples. For fine-tuning, each training example should consist of a single input prompt and its desired completion output. You don't need to give detailed instructions or multiple completion examples for the same prompt.
-
-The more training examples you have, the better. Fine tuning jobs will not proceed without at least 10 training examples, but such a small number is not enough to noticeably influence model responses. It is best practice to provide hundreds, if not thousands, of training examples to be successful.
-
-In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data, without first pruning the dataset for only the highest quality examples you could end up with a model that performs much worse than expected.
-
-### OpenAI CLI data preparation tool
-
-OpenAI's CLI data preparation tool was developed for the previous generation of fine-tuning models to assist with many of the data preparation steps. This tool will only work for data preparation for models that work with the completion API like `babbage-002` and `davinci-002`. The tool validates, gives suggestions, and reformats your data into a JSONL file ready for fine-tuning.
-
-To install the OpenAI CLI, run the following Python command:
-
-```console
-pip install openai==0.28.1
-```
-
-To analyze your training data with the data preparation tool, run the following Python command. Replace the _\<LOCAL_FILE>_ argument with the full path and file name of the training data file to analyze:
-
-```console
-openai tools fine_tunes.prepare_data -f <LOCAL_FILE>
-```
-
-This tool accepts files in the following data formats, if they contain a prompt and a completion column/key:
-
-- Comma-separated values (CSV)
-- Tab-separated values (TSV)
-- Microsoft Excel workbook (XLSX)
-- JavaScript Object Notation (JSON)
-- JSON Lines (JSONL)
-
-After it guides you through the process of implementing suggested changes, the tool reformats your training data and saves output into a JSONL file ready for fine-tuning.
-
----
-
 ## Upload your training data
 
 The next step is to either choose existing prepared training data or upload new prepared training data to use when customizing your model. After you prepare your training data, you can upload your files to the service. There are two ways to upload training data:
@@ -209,7 +155,7 @@ import os
 openai.api_key = os.getenv("AZURE_OPENAI_API_KEY") 
 openai.api_base =  os.getenv("AZURE_OPENAI_ENDPOINT")
 openai.api_type = 'azure'
-openai.api_version = '2024-02-01' # This API version or later is required to access fine-tuning for turbo/babbage-002/davinci-002
+openai.api_version = '2024-02-01' # This API version or later is required
 
 training_file_name = 'training_set.jsonl'
 validation_file_name = 'validation_set.jsonl'
@@ -302,7 +248,7 @@ from openai import AzureOpenAI
 client = AzureOpenAI(
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
   api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-02-01"  # This API version or later is required to access fine-tuning for turbo/babbage-002/davinci-002
+  api_version="2024-02-01"  # This API version or later is required
 )
 
 client.fine_tuning.jobs.create(
@@ -580,7 +526,7 @@ az cognitiveservices account deployment create
 
 ## Use a deployed customized model
 
-After your custom model deploys, you can use it like any other deployed model. You can use the **Playgrounds** in [Azure AI Foundry](https://ai.azure.com) to experiment with your new deployment. You can continue to use the same parameters with your custom model, such as `temperature` and `max_tokens`, as you can with other deployed models. For fine-tuned `babbage-002` and `davinci-002` models you will use the Completions playground and the Completions API. For fine-tuned `gpt-35-turbo-0613` models you will use the Chat playground and the Chat completion API.
+After your custom model deploys, you can use it like any other deployed model. You can use the **Chat Playground** in [Azure AI Foundry](https://ai.azure.com) to experiment with your new deployment. You can continue to use the same parameters with your custom model, such as `temperature` and `max_tokens`, as you can with other deployed models.
 
 # [OpenAI Python 1.x](#tab/python-new)