I've been reading up a lot on Open Source LLMs and with the recent release of Llama 2, I've a question.
Since Llama 2 is on Azure now, as a layman/newbie I want to know how I can actually deploy and use the model on Azure. I want to create a real-time endpoint for Llama 2. I see VMs with min. $6 per hour that I can deploy Llama 2 7B on... the cost of which confuses me (does the VM run constantly?).
Does anyone know how to deploy and how much it could cost to run Llama 2 (say 7B) on Azure?
I tried deploying a real-time Llama 2 7B endpoint on Azure through Azure AI ML studio. Confused with the right way to go about deploying such model endpoints.
