John U. Balis

@johnubalis
65 Followers
350 Following
63 Posts

Open source AI enthusiast.

Maintainer of several generative AI open source projects on Github.

I post about AI and open source.

Bloghttps://balisujohn.github.io/
Githubhttps://github.com/balisujohn
Another feature of localpilot is prompt-based selection editing, which can be quite powerful with a powerful underlying model. Here is what's already possible on CPU with a 13b parameter model:

If you are interested in using #codellama or #wizardcoder with #vscode, I have a foss #vscode / #vscodium extension which allows for fairly flexible code editing using these models.

https://github.com/balisujohn/localpilot

Since it uses #text-generation-webui as a backend, it's compatible with machines with and without GPUs and doesn't require a Docker server like Fauxpilot.

This demo is local CPU inference only with a laptop i7, with the model WizardCoder python 13b.

GitHub - balisujohn/localpilot: codellama on CPU without Docker

codellama on CPU without Docker. Contribute to balisujohn/localpilot development by creating an account on GitHub.

GitHub