update

Author: mrbullwinkle

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

@@ -23,7 +23,7 @@ manager: nitinme
 | `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 |
-| `gpt-4o` <sup>**1**</sup> (2024-08-06) | East US2 <br> North Central US <br> Sweden Central | Input: 128,000 <br> Output: 16,384  <br> Training example context length: 64,536 | Oct 2023 | 
+| `gpt-4o-mini` (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 |
+| `gpt-4o` (2024-08-06) | East US2 <br> 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 is currently in public preview.

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

@@ -86,6 +86,12 @@ Multiple turns of a conversation in a single line of your jsonl training file is
 {"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "How far is the Moon from Earth?"}, {"role": "assistant", "content": "384,400 kilometers", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Around 384,400 kilometers. Give or take a few, like that really matters.", "weight": 1}]}
 ```
 
+## Chat completions with vision
+
+```json
+{"messages": [{"role": "user", "content": [{"type": "text", "text": "What's in this image?"}, {"type": "image_url", "image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}, {"role": "assistant", "content": "The image depicts a serene landscape featuring a wooden pathway that winds through lush green grass and vegetation. The sky above is partly cloudy with a blue hue, suggesting a pleasant day. The pathway leads into the distance, surrounded by various trees and bushes on either side. This scene evokes a sense of tranquility and connection with nature."}]}
+```
+
 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

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

@@ -10,17 +10,30 @@ ms.custom:
   - ignite-2023
   - references_regions
 ms.topic: whats-new
-ms.date: 10/22/2024
+ms.date: 11/12/2024
 recommendations: false
 ---
 
 # What's new in Azure OpenAI Service
 
 This article provides a summary of the latest releases and major documentation updates for Azure OpenAI.
 
+## November 2024
+
+### Vision Fine-tuning GA
+
+Vision fine-tuning with GPT-4o (2024-08-06) in now Generally Available (GA).
+
+[Vision fine-tuning](./how-to/fine-tuning.md) allows you to add images to your JSONL training data. Just as you can send one or many image inputs to chat completions, you can include those same message types within your training data. Images can be provided either as URLs or as base64 encoded images. 
+
+For fine-tuning model region availability see, the [models page](./concepts/models.md#fine-tuning-models).
+
+### NEW Global provisioned deployment type
+
 ## October 2024
 
 ### NEW data zone standard deployment type
+
 Data zone standard deployments are available in the same Azure OpenAI resource as all other Azure OpenAI deployment types but allow you to leverage Azure global infrastructure to dynamically route traffic to the data center within the Microsoft defined data zone with the best availability for each request. Data zone standard provides higher default quotas than our Azure geography-based deployment types.  Data zone standard deployments are supported on `gpt-4o-2024-08-06`, `gpt-4o-2024-05-13`, and `gpt-4o-mini-2024-07-18` models.
 
 For more information, see the [deployment types guide](https://aka.ms/aoai/docs/deployment-types).