fixing links

Author: Blackmist

articles/ai-foundry/how-to/deploy-models-cohere-rerank.md

@@ -28,7 +28,7 @@ Cohere offers rerank models in [Azure AI Foundry](https://ai.azure.com). These m
 - Cohere Rerank v3 - English
 - Cohere Rerank v3 - Multilingual
 
-You can browse the Cohere family of models in the [Model Catalog](model-catalog.md) by filtering on the Cohere collection.
+You can browse the Cohere family of models in the [Model Catalog](./model-catalog-overview.md) by filtering on the Cohere collection.
 
 # [Cohere Rerank v3.5](#tab/cohere-rerank-3-5)
 

articles/ai-foundry/how-to/deploy-models-deepseek.md

@@ -1144,7 +1144,7 @@ Quota is managed per deployment. Each deployment has a rate limit of 200,000 tok
 ## Related content
 
 * [Explore DeepSeek-related Azure samples in various languages](https://github.com/azure-samples/deepseek)
-* [Azure AI Model Inference API](../reference/reference-model-inference-api.md)
+* [Azure AI Model Inference API](../model-inference/reference/reference-model-inference-api.md)
 * [Deploy models as serverless APIs](deploy-models-serverless.md)
 * [Consume serverless API endpoints from a different Azure AI Studio project or hub](deploy-models-serverless-connect.md)
 * [Region availability for models in serverless API endpoints](deploy-models-serverless-availability.md)