Creating a preview note for maas models

msakande · msakande · commit babe796b416e · 2024-10-10T11:27:07.000-05:00
diff --git a/articles/ai-studio/how-to/deploy-models-cohere-command.md b/articles/ai-studio/how-to/deploy-models-cohere-command.md
@@ -21,7 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Cohere Command chat models and how to use them.
 The Cohere family of models includes various models optimized for different use cases, including chat completions, embeddings, and rerank. Cohere models are optimized for various use cases that include reasoning, summarization, and question answering.
 
-
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-cohere-embed.md b/articles/ai-studio/how-to/deploy-models-cohere-embed.md
@@ -21,7 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-embeddings
 In this article, you learn about Cohere Embed V3 models and how to use them with Azure AI Studio.
 The Cohere family of models includes various models optimized for different use cases, including chat completions, embeddings, and rerank. Cohere models are optimized for various use cases that include reasoning, summarization, and question answering.
 
-
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-cohere-rerank.md b/articles/ai-studio/how-to/deploy-models-cohere-rerank.md
@@ -18,6 +18,8 @@ ms.custom: references_regions, build-2024
 
 In this article, you learn about the Cohere Rerank models, how to use Azure AI Studio to deploy them as serverless APIs with pay-as-you-go token-based billing, and how to work with the deployed models.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 ## Cohere Rerank models
 
 Cohere offers two Rerank models in [Azure AI Studio](https://ai.azure.com). These models are available in the model catalog for deployment as serverless APIs:
diff --git a/articles/ai-studio/how-to/deploy-models-jais.md b/articles/ai-studio/how-to/deploy-models-jais.md
@@ -25,7 +25,7 @@ JAIS 30b Chat is an autoregressive bi-lingual LLM for **Arabic** & **English**.
 * **Input:** Model input is text only.
 * **Output:** Model generates text only.
 
-
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-jamba.md b/articles/ai-studio/how-to/deploy-models-jamba.md
@@ -20,8 +20,10 @@ In this article, you learn how to use Azure AI Studio to deploy AI21's Jamba fam
 
 The Jamba family models are AI21's production-grade Mamba-based large language model (LLM) which leverages AI21's hybrid Mamba-Transformer architecture. It's an instruction-tuned version of AI21's hybrid structured state space model (SSM) transformer Jamba model. The Jamba family models are built for reliable commercial use with respect to quality and performance.
 
-> [!TIP]
-> See our announcements of AI21's Jamba family models available now on Azure AI Model Catalog through [AI21's blog](https://aka.ms/ai21-jamba-1.5-large-announcement) and [Microsoft Tech Community Blog](https://aka.ms/ai21-jamba-1.5-large-microsoft-annnouncement).
+See our announcements of AI21's Jamba family models available now on Azure AI Model Catalog through [AI21's blog](https://aka.ms/ai21-jamba-1.5-large-announcement) and [Microsoft Tech Community Blog](https://aka.ms/ai21-jamba-1.5-large-microsoft-annnouncement).
+
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 
 ## Deploy the Jamba family models as a serverless API
 
@@ -217,7 +219,7 @@ The `document` object has the following fields:
 - `id` (optional; str) - unique identifier. will be linked to in citations. up to 128 characters.
 - `content` (required; str) - the content of the document
 - `metadata` (optional; array of **Metadata)**
-  - `key` (required; str) - type of metadata, like ‘author’, ‘date’, ‘url’, etc. Should be things the model understands.
+  - `key` (required; str) - type of metadata, like 'author', 'date', 'url', etc. Should be things the model understands.
   - `value` (required; str) - value of the metadata
 
 #### Request example
diff --git a/articles/ai-studio/how-to/deploy-models-llama.md b/articles/ai-studio/how-to/deploy-models-llama.md
@@ -20,8 +20,9 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 
 In this article, you learn about the Meta Llama family of models and how to use them. Meta Llama models and tools are a collection of pretrained and fine-tuned generative AI text and image reasoning models - ranging in scale from SLMs (1B, 3B Base and Instruct models) for on-device and edge inferencing - to mid-size LLMs (7B, 8B and 70B Base and Instruct models) and high performant models like Meta Llama 3.1 405B Instruct for synthetic data generation and distillation use cases.
 
-> [!TIP]
-> See our announcements of Meta's Llama 3.2 family models available now on Azure AI Model Catalog through [Meta's blog](https://aka.ms/llama-3.2-meta-announcement) and [Microsoft Tech Community Blog](https://aka.ms/llama-3.2-microsoft-announcement).
+See our announcements of Meta's Llama 3.2 family models available now on Azure AI Model Catalog through [Meta's blog](https://aka.ms/llama-3.2-meta-announcement) and [Microsoft Tech Community Blog](https://aka.ms/llama-3.2-microsoft-announcement).
+
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-mistral-nemo.md b/articles/ai-studio/how-to/deploy-models-mistral-nemo.md
@@ -21,6 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Mistral Nemo chat model and how to use them.
 Mistral AI offers two categories of models. Premium models including [Mistral Large and Mistral Small](deploy-models-mistral.md), available as serverless APIs with pay-as-you-go token-based billing. Open models including [Mistral Nemo](deploy-models-mistral-nemo.md), [Mixtral-8x7B-Instruct-v01, Mixtral-8x7B-v01, Mistral-7B-Instruct-v01, and Mistral-7B-v01](deploy-models-mistral-open.md); available to also download and run on self-hosted managed endpoints.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-mistral-open.md b/articles/ai-studio/how-to/deploy-models-mistral-open.md
@@ -21,6 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Mistral-7B and Mixtral chat models and how to use them.
 Mistral AI offers two categories of models. Premium models including [Mistral Large and Mistral Small](deploy-models-mistral.md), available as serverless APIs with pay-as-you-go token-based billing. Open models including [Mistral Nemo](deploy-models-mistral-nemo.md), [Mixtral-8x7B-Instruct-v01, Mixtral-8x7B-v01, Mistral-7B-Instruct-v01, and Mistral-7B-v01](deploy-models-mistral-open.md); available to also download and run on self-hosted managed endpoints.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-mistral.md b/articles/ai-studio/how-to/deploy-models-mistral.md
@@ -21,6 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Mistral premium chat models and how to use them.
 Mistral AI offers two categories of models. Premium models including [Mistral Large and Mistral Small](deploy-models-mistral.md), available as serverless APIs with pay-as-you-go token-based billing. Open models including [Mistral Nemo](deploy-models-mistral-nemo.md), [Mixtral-8x7B-Instruct-v01, Mixtral-8x7B-v01, Mistral-7B-Instruct-v01, and Mistral-7B-v01](deploy-models-mistral-open.md); available to also download and run on self-hosted managed endpoints.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-phi-3-5-vision.md b/articles/ai-studio/how-to/deploy-models-phi-3-5-vision.md
@@ -21,7 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Phi-3.5 chat model with vision and how to use them.
 The Phi-3.5 small language models (SLMs) are a collection of instruction-tuned generative text models.
 
-
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-phi-3-vision.md b/articles/ai-studio/how-to/deploy-models-phi-3-vision.md
@@ -21,7 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Phi-3 chat model with vision and how to use them.
 The Phi-3 family of small language models (SLMs) is a collection of instruction-tuned generative text models.
 
-
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-phi-3.md b/articles/ai-studio/how-to/deploy-models-phi-3.md
@@ -21,7 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about Phi-3 family chat models and how to use them.
 The Phi-3 family of small language models (SLMs) is a collection of instruction-tuned generative text models.
 
-
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
 
 ::: zone pivot="programming-language-python"
 
diff --git a/articles/ai-studio/how-to/deploy-models-serverless-availability.md b/articles/ai-studio/how-to/deploy-models-serverless-availability.md
@@ -20,6 +20,8 @@ ms.custom:
 
 In this article, you learn about which regions are available for each of the models supporting serverless API endpoint deployments.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 Certain models in the model catalog can be deployed as a serverless API with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need. This deployment option doesn't require quota from your subscription.
 
 ## Region availability
diff --git a/articles/ai-studio/how-to/deploy-models-serverless-connect.md b/articles/ai-studio/how-to/deploy-models-serverless-connect.md
@@ -19,6 +19,8 @@ ms.custom:
 
 In this article, you learn how to configure an existing serverless API endpoint in a different project or hub than the one that was used to create the deployment.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 [Certain models in the model catalog](deploy-models-serverless-availability.md) can be deployed as serverless APIs. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need. This deployment option doesn't require quota from your subscription.
 
 The need to consume a serverless API endpoint in a different project or hub than the one that was used to create the deployment might arise in situations such as these:
diff --git a/articles/ai-studio/how-to/deploy-models-serverless.md b/articles/ai-studio/how-to/deploy-models-serverless.md
@@ -17,6 +17,8 @@ ms.custom: build-2024, serverless, devx-track-azurecli
 
 In this article, you learn how to deploy a model from the model catalog as a serverless API with pay-as-you-go token based billing.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 [Certain models in the model catalog](deploy-models-serverless-availability.md) can be deployed as a serverless API with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need. This deployment option doesn't require quota from your subscription.
 
 This article uses a Meta Llama model deployment for illustration. However, you can use the same steps to deploy any of the [models in the model catalog that are available for serverless API deployment](deploy-models-serverless-availability.md).
diff --git a/articles/ai-studio/how-to/deploy-models-timegen-1.md b/articles/ai-studio/how-to/deploy-models-timegen-1.md
@@ -22,6 +22,8 @@ You filter on the Nixtla collection to browse the TimeGEN-1 model in the [Model
 
 The Nixtla TimeGEN-1 is a generative, pretrained forecasting and anomaly detection model for time series data. TimeGEN-1 can produce accurate forecasts for new time series without training, using only historical values and exogenous covariates as inputs.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 ## Deploy TimeGEN-1 as a serverless API
 
 Certain models in the model catalog can be deployed as a serverless API with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need. This deployment option doesn't require quota from your subscription.
diff --git a/articles/ai-studio/how-to/fine-tune-model-llama.md b/articles/ai-studio/how-to/fine-tune-model-llama.md
@@ -25,6 +25,8 @@ In this article, you learn how to fine-tune Meta Llama models in [Azure AI Studi
 
 The [Meta Llama family of large language models (LLMs)](./deploy-models-llama.md) is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. The model family also includes fine-tuned versions optimized for dialogue use cases with Reinforcement Learning from Human Feedback (RLHF), called Llama-Instruct.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 ## Models
 # [Meta Llama 3.1](#tab/llama-three)
 
diff --git a/articles/ai-studio/how-to/fine-tune-phi-3.md b/articles/ai-studio/how-to/fine-tune-phi-3.md
@@ -8,14 +8,19 @@ ms.custom:
 ms.topic: how-to
 ms.date: 7/16/2024
 ---
+
 # Fine-tune Phi-3 models in Azure AI Studio
 
+[!INCLUDE [Feature preview](~/reusable-content/ce-skilling/azure/includes/ai-studio/includes/feature-preview.md)]
+
 Azure AI Studio lets you tailor large language models to your personal datasets by using a process known as fine-tuning. Fine-tuning provides significant value by enabling customization and optimization for specific tasks and applications. It leads to improved performance, cost efficiency, reduced latency, and tailored outputs.
 
 In this article, you learn how to fine-tune Phi-3 family of small language models (SLMs) in Azure AI Studio as a service with pay-as you go billing.
 
 The Phi-3 family of SLMs is a collection of instruction-tuned generative text models.  Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across various language, reasoning, coding, and math benchmarks.
 
+[!INCLUDE [maas-models-preview](../includes/maas-models-preview.md)]
+
 ## [Phi-3-mini](#tab/phi-3-mini)
 
 Phi-3 Mini is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-3 model family, and the Mini version comes in two variants 4K and 128K which is the context length (in tokens) it can support.
@@ -130,8 +135,8 @@ To fine-tune a Phi-3 model:
 
     > [!NOTE]
     > If the you have your training/validation files in a credential less datastore, you will need to allow workspace managed identity access to your datastore in order to proceed with MaaS fine-tuning with a credential less storage. On the "Datastore" page, after clicking "Update authentication" > Select the following option: 
-	
-	![Use workspace managed identity for data preview and profiling in Azure Machine Learning Studio.](../media/how-to/fine-tune/phi-3/credentials.png)
+    
+    ![Use workspace managed identity for data preview and profiling in Azure Machine Learning Studio.](../media/how-to/fine-tune/phi-3/credentials.png)
 
     Make sure all your training examples follow the expected format for inference. To fine-tune models effectively, ensure a balanced and diverse dataset. This involves maintaining data balance, including various scenarios, and periodically refining training data to align with real-world expectations, ultimately leading to more accurate and balanced model responses.
     - The batch size to use for training. When set to -1, batch_size is calculated as 0.2% of examples in training set and the max is 256.
@@ -167,8 +172,8 @@ To fine-tune a Phi-3 model:
 
     > [!NOTE]
     > If you have your training/validation files in a credential less datastore, you will need to allow workspace managed identity access to your datastore in order to proceed with MaaS finetuning with a credential less storage. On the "Datastore" page, after clicking "Update authentication" > Select the following option: 
-	
-	![Use workspace managed identity for data preview and profiling in Azure Machine Learning Studio.](../media/how-to/fine-tune/phi-3/credentials.png)
+    
+    ![Use workspace managed identity for data preview and profiling in Azure Machine Learning Studio.](../media/how-to/fine-tune/phi-3/credentials.png)
 
     Make sure all your training examples follow the expected format for inference. To fine-tune models effectively, ensure a balanced and diverse dataset. This involves maintaining data balance, including various scenarios, and periodically refining training data to align with real-world expectations, ultimately leading to more accurate and balanced model responses.
     - The batch size to use for training. When set to -1, batch_size is calculated as 0.2% of examples in training set and the max is 256.
diff --git a/articles/ai-studio/how-to/model-catalog-overview.md b/articles/ai-studio/how-to/model-catalog-overview.md
@@ -22,7 +22,7 @@ The model catalog in Azure AI Studio is the hub to discover and use a wide range
 
 ## Model collections
 
-The model catalog organizes models into three types collections:
+The model catalog organizes models into three collections:
 
 * **Curated by Azure AI**: The most popular non-Microsoft open-weight and proprietary models packaged and optimized to work seamlessly on the Azure AI platform. Use of these models is subject to the model providers' license terms. When you deploy these models in Azure AI Studio, their availability is subject to the applicable [Azure service-level agreement (SLA)](https://www.microsoft.com/licensing/docs/view/Service-Level-Agreements-SLA-for-Online-Services), and Microsoft provides support for deployment problems.
 
diff --git a/articles/ai-studio/includes/maas-models-preview.md b/articles/ai-studio/includes/maas-models-preview.md
@@ -0,0 +1,13 @@
+---
+title: include file
+description: include file
+author: msakande
+ms.author: mopeakande
+ms.service: azure-ai-studio
+ms.topic: include
+ms.date: 10/10/2024
+ms.custom: include file
+---
+
+> [!IMPORTANT]
+> A model discussed in this article might be in preview mode. If so, the model is marked as _preview_ in the model catalog.
