Llama3-70b and phi-3-128k as Copilot in VSCode powered by NVIDIA AI 🤯 Now you can use these two models within VSCode using the NVIDIA AI API In this thread 🧵, I'll walk you through the integration process, explaining each step simply and clearly👇

First, create your account on the NVIDIA AI platform Go to: click on ‘Try Now’, which will redirect you to this platform:

Then, click on ‘Login’

Enter your email, and you will be redirected to the page to create an account.

Fill in the information and click on ‘Create Account’.

Once your account is created and verified, return to the platform to get your API Key Click on the Llama3–70b-instruct model.

Click on ‘Get API Key’, generate an copy your API Key

In VSCode install the CodeGPT extension

Within the CodeGPT tab, select NVIDIA as the provider

Select ‘Edit Connections’ and paste your API Key, then click on ‘Connect’

With your account connected, now you just need to select the model ‘meta/llama3–70b-instruct’, or we also recommend trying the model ‘microsoft/phi-3-mini-128k-instruct’ which is already available

That's all! If you want to read the full article, here's the link: