Merge pull request #231385 from mrbullwinkle/mrb_03_20_2023_pm_feedback

prmerger-automator[bot] · web-flow · commit e597b5472621 · 2023-03-20T17:11:43.000Z
[Cognitive Services] [Release branch] PM feedback
diff --git a/articles/cognitive-services/openai/concepts/models.md b/articles/cognitive-services/openai/concepts/models.md
@@ -60,8 +60,7 @@ We recommend starting with the most capable model in a model family to confirm w
 
 GPT-4 is a large multimodal model meaning while it currently accepts text inputs and emits text outputs. It will eventually be able to accept image inputs as well. GPT-4 can solve difficult problems with greater accuracy than any of OpenAI's previous models. Like gpt-35-turbo, GPT-4 is optimized for chat but works well for traditional completions tasks.
 
- These models are currently in limited preview. For access, existing Azure OpenAI customers can [apply by filling out this form](https://aka.ms/oai/get-gpt4). .
-
+ These models are currently in limited preview. For access, existing Azure OpenAI customers can [apply by filling out this form](https://aka.ms/oai/get-gpt4).
 - `gpt-4`
 - `gpt-4-32k`
 
@@ -197,10 +196,10 @@ When using our embeddings models, keep in mind their limitations and risks.
 
 |  Model ID                | Supports Completions | Supports Embeddings |  Base model Regions       | Fine-Tuning Regions | Max Request (tokens) | Training Data (up to)  |
 |  ----------------------- | -------------------- | ------------------- | ------------------------- | ------------------- | -------------------- | ---------------------- |
-| `gpt-4` <sup>1</sup><sup>2</sup>     | Yes                  | No                  | East US, South Central US |  N/A                | 8,192                | September 2021         |
-| `gpt-4-32k` <sup>1</sup><sup>2</sup> | Yes                  | No                  | East US, South Central US |  N/A                | 32,768               | September 2021         |
+| `gpt-4` <sup>1,</sup><sup>2</sup>     | Yes                  | No                  | East US, South Central US |  N/A                | 8,192                | September 2021         |
+| `gpt-4-32k` <sup>1,</sup><sup>2</sup> | Yes                  | No                  | East US, South Central US |  N/A                | 32,768               | September 2021         |
 
-<sup>1</sup> The model is in limited preview and only available by request.
+<sup>1</sup> The model is in limited preview and only available by request.<br>
 <sup>2</sup> Currently, only version `0314` of this model is available.
 
 ### Codex Models
diff --git a/articles/cognitive-services/openai/how-to/chatgpt.md b/articles/cognitive-services/openai/how-to/chatgpt.md
@@ -23,7 +23,7 @@ In Azure OpenAI there are two different options for interacting with these model
 
 The ChatCompletion API is a new dedicated API for interacting with the ChatGPT and GPT-4 models. This API is the preferred method for accessing these models.
 
-ChatML uses the same [completion API](../reference.md#completions) that you use for other models like text-davinci-002, it requires a unique token based prompt format known as Chat Markup Language (ChatML). This provides lower level access than the dedicated ChatCompletion API, but also requires additional input validation and the underlying format is more likely to change over time.
+ChatML uses the same [completion API](../reference.md#completions) that you use for other models like text-davinci-002, it requires a unique token based prompt format known as Chat Markup Language (ChatML). This provides lower level access than the dedicated ChatCompletion API, but also requires additional input validation and **the underlying format is more likely to change over time**.
 
 This article walks you through getting started with the new ChatGPT and GPT-4 models. It's important to use the techniques described here to get the best results. If you try to interact with the models the same way you did with the older model series, the models will often be verbose and provide less useful responses.
 
diff --git a/articles/cognitive-services/openai/overview.md b/articles/cognitive-services/openai/overview.md
@@ -22,7 +22,7 @@ Azure OpenAI Service provides REST API access to OpenAI's powerful language mode
 
 | Feature | Azure OpenAI |
 | --- | --- |
-| Models available | **NEW GPT-4 series (limited preview)** <br> GPT-3 base series <br>**New ChatGPT (gpt-35-turbo)**<br> Codex series <br> Embeddings series <br> Learn more in our [Models](./concepts/models.md) page.|
+| Models available | **NEW GPT-4 series (limited preview)** <br> GPT-3 base series <br>**NEW ChatGPT (gpt-35-turbo)**<br> Codex series <br> Embeddings series <br> Learn more in our [Models](./concepts/models.md) page.|
 | Fine-tuning | Ada <br> Babbage <br> Curie <br> Cushman* <br> Davinci* <br> \* Currently unavailable. \*\*East US and West Europe Fine-tuning is currently unavailable to new customers. Please use US South Central for US based training|
 | Price | [Available here](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) |
 | Virtual network support & private link support | Yes | 
@@ -124,7 +124,11 @@ The number of examples typically range from 0 to 100 depending on how many can f
 
 ### Models
 
-The service provides users access to several different models. Each model provides a different capability and price point. The GPT-3 base models are known as Davinci, Curie, Babbage, and Ada in decreasing order of capability and increasing order of speed.
+The service provides users access to several different models. Each model provides a different capability and price point.
+
+GPT-4 models are the latest available models. These models are currently in limited preview. For access, existing Azure OpenAI customers can [apply by filling out this form](https://aka.ms/oai/get-gpt4).
+
+The GPT-3 base models are known as Davinci, Curie, Babbage, and Ada in decreasing order of capability and increasing order of speed.
 
 The Codex series of models is a descendant of GPT-3 and has been trained on both natural language and code to power natural language to code use cases. Learn more about each model on our [models concept page](./concepts/models.md).
 
diff --git a/articles/cognitive-services/openai/whats-new.md b/articles/cognitive-services/openai/whats-new.md
@@ -17,7 +17,7 @@ keywords:
 
 ## March 2023
 
-- **GPT-4 series models are now available in limited preview on Azure OpenAI**. To request access, existing Azure OpenAI customers can [apply by filling out this form](https://aka.ms/oai/get-gpt4).
+- **GPT-4 series models are now available in limited preview on Azure OpenAI**. To request access, existing Azure OpenAI customers can [apply by filling out this form](https://aka.ms/oai/get-gpt4). These models are currently available in the East US and South Central US regions.
 
 - **New ChatGPT API released in public preview on 3/21**. To learn more checkout the [updated quickstarts](./quickstart.md) and [how-to article](./how-to/chatgpt.md).
 
