Meta LLama 2 Foundational Model with Prompt Flow

[@IQmates]

This is a great demo. We are currently trying to deploy Llama 2 but the problem is the expensive GPUs if you deploy it in the manner shown here so we have downloaded quantized models. Getting those to work has been quite the challenge.

[@SimonSamnegard]

Have you got it to work? From where did you get the quantized models?

[@elbruno]

This is awesome! Thanks for adding the Prompt Flow demo 👍

[@BrianGitau-s2h]

Its a really nice tutorial, but I wonder why they would skip past the part where you have to request a GPU that will cost you $9106.56/month. But great job all around!

[@SimonSamnegard]

lol

[@KxetaHealth]

True

[@GangxinLi]

Yeah huge cost

[@ArunKumar-bp5lo]

Thanks for sharing

[@learnwithgirishgoudar]

can you provide the link to the demo

[@BrokenRecord-i7q]

where can I get the code!