Merge pull request #281557 from ssalgadodev/patch-130

Fast Follow Updates Llama 3.1

Author: prmerger-automator[bot]

articles/ai-studio/concepts/fine-tuning-overview.md

@@ -99,8 +99,8 @@ There isn't a single right answer to this question, but you should have clearly
 
 Now that you know when to leverage fine-tuning for your use-case, you can go to Azure AI Studio to find several models available to fine-tune including:
 - Azure OpenAI models
-- Llama 2 family models
-- Llama 3.1 family of models
+- Meta Llama 2 family models
+- Meta Llama 3.1 family of models
 
 
 ### Azure OpenAI models
@@ -121,16 +121,16 @@ Please note for fine-tuning Azure OpenAI models, you must add a connection to an
 
 ### Llama 2 family models
 The following Llama 2 family models are supported in Azure AI Studio for fine-tuning:
-- `Llama-2-70b`
-- `Llama-2-7b`
-- `Llama-2-13b`
+- `Meta-Llama-2-70b`
+- `Meta-Llama-2-7b`
+- `Meta-Llama-2-13b`
 
 Fine-tuning of Llama 2 models is currently supported in projects located in West US 3.
 
 ### Llama 3.1 family models
 The following Llama 3.1 family models are supported in Azure AI Studio for fine-tuning:
-- `Llama-3.1-70b`
-- `Llama-3.1-7b`
+- `Meta-Llama-3.1-70b-Instruct`
+- `Meta-Llama-3.1-7b-Instruct`
 
 Fine-tuning of Llama 3.1 models is currently supported in projects located in West US 3.
 

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

@@ -5,7 +5,7 @@ description: Learn how to deploy Meta Llama 3.1 models with Azure AI Studio.
 manager: scottpolly
 ms.service: azure-ai-studio
 ms.topic: how-to
-ms.date: 5/21/2024
+ms.date: 7/21/2024
 ms.reviewer: shubhiraj
 reviewer: shubhirajMsft
 ms.author: ssalgado

articles/ai-studio/how-to/fine-tune-model-llama.md

@@ -5,7 +5,7 @@ description: Learn how to fine-tune Meta Llama models in Azure AI Studio.
 manager: scottpolly
 ms.service: azure-ai-studio
 ms.topic: how-to
-ms.date: 7/18/2024
+ms.date: 7/23/2024
 ms.reviewer: rasavage
 reviewer: shubhirajMsft
 ms.author: ssalgado
@@ -30,18 +30,18 @@ The [Meta Llama family of large language models (LLMs)](./deploy-models-llama.md
 
 The following models are available in Azure Marketplace for Llama 3.1 when fine-tuning as a service with pay-as-you-go billing:
 
-- `Llama-3.1-80B-Instruct` (preview)
-- `LLama-3.1-8b-Instruct` (preview)
+- `Meta-Llama-3.1-80B-Instruct` (preview)
+- `Meta-LLama-3.1-8b-Instruct` (preview)
 ![IMPORTANT]
-> At this time we can not do fine-tuning for Llama 3.1 with context length of 128K. The current context length is limited to 65k.
+> At this time we are not able to do fine-tuning for Llama 3.1 with sequence length of 128K. 
 
 # [Meta Llama 2](#tab/llama-two)
 
 The following models are available in Azure Marketplace for Llama 2 when fine-tuning as a service with pay-as-you-go billing:
 
-- `Llama-2-70b` (preview)
-- `Llama-2-13b` (preview)
-- `Llama-2-7b` (preview)
+- `Meta Llama-2-70b` (preview)
+- `Meta Llama-2-13b` (preview)
+- `Meta Llama-2-7b` (preview)
 
 Fine-tuning of Llama 2 models is currently supported in projects located in West US 3.
 
@@ -192,7 +192,7 @@ To fine-tune a LLama 3.1 model:
 1. Select training data to fine-tune your model. See [data preparation](#data-preparation) for more information.
 
     > [!NOTE]
-    > If the you has their training/validation files in a credential less datastore, they will need to allow workspace managed identity access to their datastore in order to proceed with MaaS finetuning with a credential less storage. That would be this setting on the "Datastore" page, after clicking "Update authentication" > Select the following option: 
+    > If you have your training/validation files in a credential less datastore, you will need to allow workspace managed identity access to their 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/llama/credentials.png)
 

articles/machine-learning/how-to-deploy-models-llama.md

@@ -6,7 +6,7 @@ manager: scottpolly
 ms.service: machine-learning
 ms.subservice: inferencing
 ms.topic: how-to
-ms.date: 07/16/2024
+ms.date: 07/23/2024
 ms.reviewer: shubhiraj
 reviewer: shubhirajMsft
 ms.author: ssalgado