Merge pull request #1988 from MicrosoftDocs/release-preview-new-mistral-models

Release preview new mistral models -> main -- 12/13 - 04:30 AM PST

Author: Albertyang0

articles/ai-studio/how-to/deploy-models-mistral.md

@@ -5,7 +5,7 @@ description: Learn how to use Mistral premium chat models with Azure AI Foundry.
 ms.service: azure-ai-studio
 manager: scottpolly
 ms.topic: how-to
-ms.date: 10/23/2024
+ms.date: 11/20/2024
 ms.reviewer: kritifaujdar
 reviewer: fkriti
 ms.author: mopeakande
@@ -31,27 +31,33 @@ The Mistral premium chat models include the following models:
 
 # [Mistral Large](#tab/mistral-large)
 
-Mistral Large is Mistral AI's most advanced Large Language Model (LLM). It can be used on any language-based task, thanks to its state-of-the-art reasoning and knowledge capabilities.
+Mistral Large models are Mistral AI's most advanced Large Language Models (LLM). They can be used on any language-based task, thanks to their state-of-the-art reasoning, knowledge, and coding capabilities. Several Mistral Large model variants are available, and their attributes are as follows.
 
-Additionally, Mistral Large is:
+Attributes of **Mistral Large (2402)**, also abbreviated as Mistral Large, include:
 
 * **Specialized in RAG**. Crucial information isn't lost in the middle of long context windows (up to 32-K tokens).
 * **Strong in coding**. Code generation, review, and comments. Supports all mainstream coding languages.
 * **Multi-lingual by design**. Best-in-class performance in French, German, Spanish, Italian, and English. Dozens of other languages are supported.
 * **Responsible AI compliant**. Efficient guardrails baked in the model and extra safety layer with the safe_mode option.
 
-And attributes of Mistral Large (2407) include:
+Attributes of **Mistral Large (2407)** include:
 
 * **Multi-lingual by design**. Supports dozens of languages, including English, French, German, Spanish, and Italian.
 * **Proficient in coding**. Trained on more than 80 coding languages, including Python, Java, C, C++, JavaScript, and Bash. Also trained on more specific languages such as Swift and Fortran.
 * **Agent-centric**. Possesses agentic capabilities with native function calling and JSON outputting.
 * **Advanced in reasoning**. Demonstrates state-of-the-art mathematical and reasoning capabilities.
 
+Attributes of **Mistral Large (2411)** include the same as Mistral Large (2407) with the following additional attributes:
+* System prompts are injected before each conversation.
+* Better performance on long content.
+* Improved function calling capabilities.
+
 
 The following models are available:
 
 * [Mistral-Large](https://aka.ms/azureai/landing/Mistral-Large)
 * [Mistral-Large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)
+* [Mistral-Large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)
 
 
 # [Mistral Small](#tab/mistral-small)
@@ -515,27 +521,33 @@ The Mistral premium chat models include the following models:
 
 # [Mistral Large](#tab/mistral-large)
 
-Mistral Large is Mistral AI's most advanced Large Language Model (LLM). It can be used on any language-based task, thanks to its state-of-the-art reasoning and knowledge capabilities.
+Mistral Large models are Mistral AI's most advanced Large Language Models (LLM). They can be used on any language-based task, thanks to their state-of-the-art reasoning, knowledge, and coding capabilities. Several Mistral Large model variants are available, and their attributes are as follows.
 
-Additionally, Mistral Large is:
+Attributes of **Mistral Large (2402)**, also abbreviated as Mistral Large, include:
 
 * **Specialized in RAG**. Crucial information isn't lost in the middle of long context windows (up to 32-K tokens).
 * **Strong in coding**. Code generation, review, and comments. Supports all mainstream coding languages.
 * **Multi-lingual by design**. Best-in-class performance in French, German, Spanish, Italian, and English. Dozens of other languages are supported.
 * **Responsible AI compliant**. Efficient guardrails baked in the model and extra safety layer with the safe_mode option.
 
-And attributes of Mistral Large (2407) include:
+Attributes of **Mistral Large (2407)** include:
 
 * **Multi-lingual by design**. Supports dozens of languages, including English, French, German, Spanish, and Italian.
 * **Proficient in coding**. Trained on more than 80 coding languages, including Python, Java, C, C++, JavaScript, and Bash. Also trained on more specific languages such as Swift and Fortran.
 * **Agent-centric**. Possesses agentic capabilities with native function calling and JSON outputting.
 * **Advanced in reasoning**. Demonstrates state-of-the-art mathematical and reasoning capabilities.
 
+Attributes of **Mistral Large (2411)** include the same as Mistral Large (2407) with the following additional attributes:
+* System prompts are injected before each conversation.
+* Better performance on long content.
+* Improved function calling capabilities.
+
 
 The following models are available:
 
 * [Mistral-Large](https://aka.ms/azureai/landing/Mistral-Large)
 * [Mistral-Large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)
+* [Mistral-Large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)
 
 
 # [Mistral Small](#tab/mistral-small)
@@ -1018,27 +1030,33 @@ The Mistral premium chat models include the following models:
 
 # [Mistral Large](#tab/mistral-large)
 
-Mistral Large is Mistral AI's most advanced Large Language Model (LLM). It can be used on any language-based task, thanks to its state-of-the-art reasoning and knowledge capabilities.
+Mistral Large models are Mistral AI's most advanced Large Language Models (LLM). They can be used on any language-based task, thanks to their state-of-the-art reasoning, knowledge, and coding capabilities. Several Mistral Large model variants are available, and their attributes are as follows.
 
-Additionally, Mistral Large is:
+Attributes of **Mistral Large (2402)**, also abbreviated as Mistral Large, include:
 
 * **Specialized in RAG**. Crucial information isn't lost in the middle of long context windows (up to 32-K tokens).
 * **Strong in coding**. Code generation, review, and comments. Supports all mainstream coding languages.
 * **Multi-lingual by design**. Best-in-class performance in French, German, Spanish, Italian, and English. Dozens of other languages are supported.
 * **Responsible AI compliant**. Efficient guardrails baked in the model and extra safety layer with the safe_mode option.
 
-And attributes of Mistral Large (2407) include:
+Attributes of **Mistral Large (2407)** include:
 
 * **Multi-lingual by design**. Supports dozens of languages, including English, French, German, Spanish, and Italian.
 * **Proficient in coding**. Trained on more than 80 coding languages, including Python, Java, C, C++, JavaScript, and Bash. Also trained on more specific languages such as Swift and Fortran.
 * **Agent-centric**. Possesses agentic capabilities with native function calling and JSON outputting.
 * **Advanced in reasoning**. Demonstrates state-of-the-art mathematical and reasoning capabilities.
 
+Attributes of **Mistral Large (2411)** include the same as Mistral Large (2407) with the following additional attributes:
+* System prompts are injected before each conversation.
+* Better performance on long content.
+* Improved function calling capabilities.
+
 
 The following models are available:
 
 * [Mistral-Large](https://aka.ms/azureai/landing/Mistral-Large)
 * [Mistral-Large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)
+* [Mistral-Large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)
 
 
 # [Mistral Small](#tab/mistral-small)
@@ -1543,27 +1561,33 @@ The Mistral premium chat models include the following models:
 
 # [Mistral Large](#tab/mistral-large)
 
-Mistral Large is Mistral AI's most advanced Large Language Model (LLM). It can be used on any language-based task, thanks to its state-of-the-art reasoning and knowledge capabilities.
+Mistral Large models are Mistral AI's most advanced Large Language Models (LLM). They can be used on any language-based task, thanks to their state-of-the-art reasoning, knowledge, and coding capabilities. Several Mistral Large model variants are available, and their attributes are as follows.
 
-Additionally, Mistral Large is:
+Attributes of **Mistral Large (2402)**, also abbreviated as Mistral Large, include:
 
 * **Specialized in RAG**. Crucial information isn't lost in the middle of long context windows (up to 32-K tokens).
 * **Strong in coding**. Code generation, review, and comments. Supports all mainstream coding languages.
 * **Multi-lingual by design**. Best-in-class performance in French, German, Spanish, Italian, and English. Dozens of other languages are supported.
 * **Responsible AI compliant**. Efficient guardrails baked in the model and extra safety layer with the safe_mode option.
 
-And attributes of Mistral Large (2407) include:
+Attributes of **Mistral Large (2407)** include:
 
 * **Multi-lingual by design**. Supports dozens of languages, including English, French, German, Spanish, and Italian.
 * **Proficient in coding**. Trained on more than 80 coding languages, including Python, Java, C, C++, JavaScript, and Bash. Also trained on more specific languages such as Swift and Fortran.
 * **Agent-centric**. Possesses agentic capabilities with native function calling and JSON outputting.
 * **Advanced in reasoning**. Demonstrates state-of-the-art mathematical and reasoning capabilities.
 
+Attributes of **Mistral Large (2411)** include the same as Mistral Large (2407) with the following additional attributes:
+* System prompts are injected before each conversation.
+* Better performance on long content.
+* Improved function calling capabilities.
+
 
 The following models are available:
 
 * [Mistral-Large](https://aka.ms/azureai/landing/Mistral-Large)
 * [Mistral-Large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)
+* [Mistral-Large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)
 
 
 # [Mistral Small](#tab/mistral-small)
@@ -2147,7 +2171,7 @@ View the response from the model:
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 

articles/ai-studio/how-to/model-catalog-overview.md

@@ -78,7 +78,7 @@ The following list contains Serverless API models. For Azure OpenAI models, see
 Model | Managed compute | Serverless API (pay-per-token)
 --|--|--
 Llama family models | Llama-3.2-3B-Instruct<BR>  Llama-3.2-1B-Instruct<BR>  Llama-3.2-1B<BR>  Llama-3.2-90B-Vision-Instruct<BR>  Llama-3.2-11B-Vision-Instruct<BR>  Llama-3.1-8B-Instruct<BR>  Llama-3.1-8B<BR>  Llama-3.1-70B-Instruct<BR>  Llama-3.1-70B<BR>  Llama-3-8B-Instruct<BR>  Llama-3-70B<BR>  Llama-3-8B<BR>  Llama-Guard-3-1B<BR>  Llama-Guard-3-8B<BR>  Llama-Guard-3-11B-Vision<BR>  Llama-2-7b<BR>  Llama-2-70b<BR>  Llama-2-7b-chat<BR>  Llama-2-13b-chat<BR>  CodeLlama-7b-hf<BR>  CodeLlama-7b-Instruct-hf<BR>  CodeLlama-34b-hf<BR>  CodeLlama-34b-Python-hf<BR>  CodeLlama-34b-Instruct-hf<BR>  CodeLlama-13b-Instruct-hf<BR>  CodeLlama-13b-Python-hf<BR>  Prompt-Guard-86M<BR>  CodeLlama-70b-hf<BR> | Llama-3.2-90B-Vision-Instruct<br>  Llama-3.2-11B-Vision-Instruct<br>  Llama-3.1-8B-Instruct<br>  Llama-3.1-70B-Instruct<br>  Llama-3.1-405B-Instruct<br>  Llama-3-8B-Instruct<br>  Llama-3-70B-Instruct<br>  Llama-2-7b<br>  Llama-2-7b-chat<br>  Llama-2-70b<br>  Llama-2-70b-chat<br>  Llama-2-13b<br>  Llama-2-13b-chat<br>
-Mistral family models | mistralai-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x22B-Instruct-v0-1 <br> mistral-community-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x7B-v01 <br> mistralai-Mistral-7B-Instruct-v0-2 <br> mistralai-Mistral-7B-v01 <br> mistralai-Mixtral-8x7B-Instruct-v01 <br> mistralai-Mistral-7B-Instruct-v01 | Mistral-large (2402) <br> Mistral-large (2407) <br> Mistral-small <br> Ministral-3B <br> Mistral-NeMo
+Mistral family models | mistralai-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x22B-Instruct-v0-1 <br> mistral-community-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x7B-v01 <br> mistralai-Mistral-7B-Instruct-v0-2 <br> mistralai-Mistral-7B-v01 <br> mistralai-Mixtral-8x7B-Instruct-v01 <br> mistralai-Mistral-7B-Instruct-v01 | Mistral-large <br> Mistral-large (2407) <br> Mistral-large (2411) <br> Mistral-small <br> Ministral-3B <br> Mistral-NeMo
 Cohere family models | Not available | Cohere-command-r-plus-08-2024 <br> Cohere-command-r-08-2024 <br> Cohere-command-r-plus <br> Cohere-command-r <br> Cohere-embed-v3-english <br> Cohere-embed-v3-multilingual <br> Cohere-rerank-v3-english <br> Cohere-rerank-v3-multilingual
 JAIS | Not available | jais-30b-chat
 AI21 family models | Not available | Jamba-1.5-Mini <br> Jamba-1.5-Large

articles/ai-studio/includes/region-availability-maas.md

@@ -60,8 +60,8 @@ Phi-3-Medium-4K-Instruct  <br>  Phi-3-Medium-128K-Instruct  | Not applicable | E
 Mistral Nemo     | [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)  <br> Brazil <br> Hong Kong <br> Israel     | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3           | Not available       |
 Ministral-3B     | [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)   <br> Brazil <br> Hong Kong <br> Israel      | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3           |  Not available       |
 Mistral Small     | [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)   <br> Brazil <br> Hong Kong <br> Israel      | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3           |  Not available       |
-Mistral Large (2402)     | [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)  <br> Brazil <br> Hong Kong <br> Israel    | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3           | Not available       |
-Mistral-Large (2407)     | [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)   <br> Brazil <br> Hong Kong <br> Israel   | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3           | Not available       |
+Mistral Large <br>  Mistral-Large (2407) <br> Mistral-Large (2411)    | [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)  <br> Brazil <br> Hong Kong <br> Israel    | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3           | Not available       |
+
 
 
 ### Nixtla models

articles/machine-learning/concept-model-catalog.md

@@ -57,7 +57,7 @@ Network isolation | Managed Virtual Network with Online Endpoints. [Learn more.]
 Model | Managed compute | Serverless API (pay-as-you-go)
 --|--|--
 Llama family models  | Llama-2-7b <br> Llama-2-7b-chat <br> Llama-2-13b <br> Llama-2-13b-chat <br> Llama-2-70b <br> Llama-2-70b-chat <br> Llama-3-8B-Instruct <br> Llama-3-70B-Instruct <br> Llama-3-8B <br> Llama-3-70B | Llama-3-70B-Instruct <br> Llama-3-8B-Instruct <br> Llama-2-7b <br> Llama-2-7b-chat <br> Llama-2-13b <br> Llama-2-13b-chat <br> Llama-2-70b <br> Llama-2-70b-chat 
-Mistral family models | mistralai-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x22B-Instruct-v0-1 <br> mistral-community-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x7B-v01 <br> mistralai-Mistral-7B-Instruct-v0-2 <br> mistralai-Mistral-7B-v01 <br> mistralai-Mixtral-8x7B-Instruct-v01 <br> mistralai-Mistral-7B-Instruct-v01 | Mistral-large (2402) <br> Mistral-large (2407) <br> Mistral-small <br> Ministral-3B <br> Mistral-Nemo
+Mistral family models | mistralai-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x22B-Instruct-v0-1 <br> mistral-community-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x7B-v01 <br> mistralai-Mistral-7B-Instruct-v0-2 <br> mistralai-Mistral-7B-v01 <br> mistralai-Mixtral-8x7B-Instruct-v01 <br> mistralai-Mistral-7B-Instruct-v01 | Mistral-large <br> Mistral-large (2407) <br> Mistral-large (2411) <br> Mistral-small <br> Ministral-3B <br> Mistral-Nemo
 Cohere family models | Not available | Cohere-command-r-plus-08-2024 <br> Cohere-command-r-08-2024 <br> Cohere-command-r-plus <br> Cohere-command-r <br> Cohere-embed-v3-english <br> Cohere-embed-v3-multilingual <br> Cohere-rerank-v3-english <br> Cohere-rerank-v3-multilingual
 JAIS | Not available | jais-30b-chat
 Phi-3 family models | Phi-3-mini-4k-Instruct <br> Phi-3-mini-128k-Instruct <br> Phi-3-small-8k-Instruct <br> Phi-3-small-128k-Instruct <br> Phi-3-medium-4k-instruct <br> Phi-3-medium-128k-instruct <br> Phi-3-vision-128k-Instruct <br> Phi-3.5-mini-Instruct <br> Phi-3.5-vision-Instruct <br> Phi-3.5-MoE-Instruct | Phi-3-mini-4k-Instruct <br> Phi-3-mini-128k-Instruct <br> Phi-3-small-8k-Instruct <br> Phi-3-small-128k-Instruct <br> Phi-3-medium-4k-instruct <br> Phi-3-medium-128k-instruct <br> <br> Phi-3.5-mini-Instruct <br> Phi-3.5-vision-Instruct <br> Phi-3.5-MoE-Instruct