Code Like a Pro: Setting Up Model Llama-3-70B as Your VS Code Copilot

[@mykojai]

This is freaking gold my friend! instant subscribe! thanks so much keep up the good work.

[@saurabhkankriya]

Welcome aboard!

[@ranjaniitr]

This is basically recommended for faster llm token inference to be used in ai playground😊

[@trustn01]

thx for this video and free usage of 70b. but it looks like, that CodeQwen1.5-7B-Chat is outperforming Llama3-70B-instruct so u can use local llm?

[@saurabhkankriya]

It's completely your call. The purpose of the demo is to show that one can replace openai models with the open source ones.

[@trustn01]

@@saurabhkankriya Yes, of course, thanks so much for the demo. just thought share some other options if anyone is interested

[@AmitDas-yb3re]

How can you do this in Jetbrains IDE?

[@saurabhkankriya]

I don't have experience with Jetbrains. You can read the continue extension's github Readme. They probably may have a documentation on this kind of integration.

[@utkarsh8719]

Revoke your api key

[@saurabhkankriya]

Thanks for pointing this out. After recording the video, I deleted the API keys.