fixing bookmarks

Author: s-polly

articles/machine-learning/how-to-deploy-models-cohere-command.md

@@ -112,7 +112,7 @@ To create a deployment:
 1. Select the endpoint to open its Details page.
 1. Select the **Test** tab to start interacting with the model.  
 1. You can always find the endpoint's details, URL, and access keys by navigating to **Workspace** > **Endpoints** > **Serverless endpoints**.
-2. Take note of the **Target** URL and the **Secret Key**. For more information on using the APIs, see the [reference](#reference-for-cohere-models-deployed-as-a-service) section.
+2. Take note of the **Target** URL and the **Secret Key**. For more information on using the APIs, see the [reference](#reference-for-cohere-models-deployed-as-a-serverless-api) section.
 
 To learn about billing for models deployed with pay-as-you-go, see [Cost and quota considerations for Cohere models deployed as a service](#cost-and-quota-considerations-for-models-deployed-as-a-service).
 
@@ -125,7 +125,7 @@ The previously mentioned Cohere models can be consumed using the chat API.
 1. Copy the **Target** URL and the **Key** token values.
 2. Cohere exposes two routes for inference with the Command R and Command R+ models. The [Azure AI Model Inference API](reference-model-inference-api.md) on the route `/chat/completions` and the native [Cohere API](#cohere-chat-api).
 
-For more information on using the APIs, see the [reference](#reference-for-cohere-models-deployed-as-a-service) section.
+For more information on using the APIs, see the [reference](#reference-for-cohere-models-deployed-as-a-serverless-api) section.
 
 ## Reference for Cohere models deployed as a serverless API
 

articles/machine-learning/how-to-deploy-models-cohere-embed.md

@@ -91,7 +91,7 @@ To create a deployment:
 1. Select the endpoint to open its Details page.
 1. Select the **Test** tab to start interacting with the model.  
 1. You can always find the endpoint's details, URL, and access keys by navigating to **Workspace** > **Endpoints** > **Serverless endpoints**.
-1. Take note of the **Target** URL and the **Secret Key**. For more information on using the APIs, see the [reference](#embed-api-reference-for-cohere-embed-models-deployed-as-a-service) section.
+1. Take note of the **Target** URL and the **Secret Key**. For more information on using the APIs, see the [reference] (#embed-api-reference-for-cohere-embed-models-deployed-as-a-serverless-api) section.
 
 To learn about billing for models deployed with pay-as-you-go, see [Cost and quota considerations for Cohere models deployed as a service](#cost-and-quota-considerations-for-models-deployed-as-a-service).
 
@@ -104,7 +104,7 @@ The previously mentioned Cohere models can be consumed using the chat API.
 1. Copy the **Target** URL and the **Key** token values.
 1. Cohere exposes two routes for inference with the Embed v3 - English and Embed v3 - Multilingual models. `v1/embeddings` adheres to the Azure AI Generative Messages API schema, and `v1/embed` supports Cohere's native API schema.
 
-    For more information on using the APIs, see the [reference](#embed-api-reference-for-cohere-embed-models-deployed-as-a-service) section.
+    For more information on using the APIs, see the [reference](#embed-api-reference-for-cohere-embed-models-deployed-as-a-serverless-api) section.
 
 ## Embed API reference for Cohere Embed models deployed as a serverless API
 

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

@@ -43,7 +43,7 @@ The following models are available in Azure Marketplace for Meta Llama models wh
 * [Meta Llama-3-8B (preview)](https://aka.ms/aistudio/landing/meta-llama-3-8b-base)
 * [Meta Llama-3-70B (preview)](https://aka.ms/aistudio/landing/meta-llama-3-70b-base)
 
-If you need to deploy a different model, [deploy it to real-time endpoints](#deploy-meta-llama-models-to-real-time-endpoints) instead.
+If you need to deploy a different model, [deploy it to managed compute](#deploy-meta-llama-models-to-managed-compute) instead.
 
 # [Meta Llama 2](#tab/llama-two)
 
@@ -54,7 +54,7 @@ If you need to deploy a different model, [deploy it to real-time endpoints](#dep
 * Meta Llama-2-70B (preview)
 * Meta Llama 2 70B-Chat (preview)
 
-If you need to deploy a different model, [deploy it to managed compute](#deploy-meta-llama-models-to-real-time-endpoints) instead.
+If you need to deploy a different model, [deploy it to managed compute](#deploy-meta-llama-models-to-managed-compute) instead.
 
 ---
 
@@ -199,7 +199,7 @@ Models deployed as a service can be consumed using either the chat or the comple
     - For completions models, such as `Llama-3-8B`, use the [`<target_url>/v1/completions`](#completions-api) API.
     - For chat models, such as `Llama-3-8B-Instruct`, use the [`<target_url>/v1/chat/completions`](#chat-api) API.
 
-   For more information on using the APIs, see the [reference](#reference-for-meta-llama-models-deployed-as-a-service) section.
+   For more information on using the APIs, see the [reference](#reference-for-meta-llama-models-deployed-a-serverless-api) section.
 
 # [Meta Llama 2](#tab/llama-two)
 
@@ -211,7 +211,7 @@ Models deployed as a service can be consumed using either the chat or the comple
     - For completions models, such as `Meta-Llama-2-7B`, use the [`/v1/completions`](#completions-api) API or the [Azure AI Model Inference API](reference-model-inference-api.md) on the route `/completions`.
     - For chat models, such as `Meta-Llama-2-7B-Chat`, use the [`/v1/chat/completions`](#chat-api) API or the [Azure AI Model Inference API](reference-model-inference-api.md) on the route `/chat/completions`.
 
-    For more information on using the APIs, see the [reference](#reference-for-meta-llama-models-deployed-as-a-service) section.
+    For more information on using the APIs, see the [reference](#reference-for-meta-llama-models-deployed-a-serverless-api) section.
 
 ---