DeepSeek R1 on Azure AI Foundry
This article is originally published at https://tomaztsql.wordpress.com
Starting with the end of January 2025, DeepSeek R1 model has had a huge impact on how the AI community, developers and general public see Generative Models. Not only that is free (as of writing this blog post), but the refinement of the information made it possible, that the models are smaller than original GPT-4 and similar. Benefiting in smaller costs for training, running and improving reasoning.
This resonates well with the concept of small language models and the idea of what Satya Nadella conceptualized on Microsoft Ignite in October of 2024 (link to video ).
In my Advent of blogposts on Microsoft Azure AI in December 2024 ( below are the links), I have mentioned and used several but at the time DeepSeek R1 was not available.
- Dec 01: Microsoft Azure AI – What is Foundry?
- Dec 02: Microsoft Azure AI – Working with Azure AI Foundry
- Dec 03: Microsoft Azure AI – Creating project in Azure AI Foundry
- Dec 04: Microsoft Azure AI – Deployment in Azure AI Foundry
- Dec 05: Microsoft Azure AI – Deployment parameters in Azure AI Foundry
- Dec 06: Microsoft Azure AI – AI Services in Azure AI Foundry
- Dec 07: Microsoft Azure AI – Speech service in AI Services
- Dec 08: Microsoft Azure AI – Speech Studio in Azure with AI Services
- Dec 09: Microsoft Azure AI – Speech SDK with Python
- Dec 10: Microsoft Azure AI – Language and Translation in Azure AI Foundry
- Dec 11: Microsoft Azure AI – Language and Translation Python SDK
- Dec 12: Microsoft Azure AI – Vision and Document AI Service
- Dec 13: Microsoft Azure AI – Vision and Document Python SDK
- Dec 14: Microsoft Azure AI – Content safety AI service
- Dec 15: Microsoft Azure AI – Content safety Python SDK
- Dec 16: Microsoft Azure AI – Fine-tuning a model
- Dec 17: Microsoft Azure AI – Azure OpenAI service
- Dec 18: Microsoft Azure AI – Azure AI Hub and Azure AI Project
- Dec 19: Microsoft Azure AI – Azure AI Foundry management center
- Dec 20: Microsoft Azure AI – Models and endpoints in Azure AI Foundry
- Dec 21: Microsoft Azure AI – Prompt flow in Azure AI Foundry
- Dec 22: Microsoft Azure AI – Prompt flow using VS Code and Python
- Dec 23: Microsoft Azure AI – Tracing in Azure AI Foundry
- Dec 24: Microsoft Azure AI – Evaluation in Azure AI Foundry
As of end of January 2025, DeepSeek R1 is available on Azure AI Foundry!
If you are starting from the scratch, here is the entry to-do, if you want to start using DeepSeekR1 model:
- Get an Azure Account (you can always try if for free)
- Navigate to azure AI Foundry and create a Hub / Project and go through setup deployment
- In the model catalog, search for DeepSeek R1
- Start using the model as a chatbot or integrate it with your applications (R1 is also available via a serverless endpoint through Azure AI Foundry)
Benefits
DeepSeek R1 has improved reasoning, and it is cheaper to use. My personal view – on understanding the costs of infrastructure, competition, development of models (and who is developing them) and the pace of development – is that model fits better in Microsoft landscape, because it is smaller, better and will consume (assuming and laying out the math behind the costs of new data centres that Microsoft, Amazon and Google are spending on yearly basis) less costs per end user to run in and to serve it for consumption / inference.
Thanks for visiting r-craft.org
This article is originally published at https://tomaztsql.wordpress.com
Please visit source website for post related comments.