Viewing profile — minosu

Mistral 7b inferences about 18% faster for me as a 4bit quantized version on an A100. Thats definitely relevant when running anything but chatbots.

Hey all! This is a lightweight Android app to auto-change your wallpaper using AI generated images, implemented via the recently introduced DALL·E 3 API. I wanted something no-fril…

This a continuation of previous work done in the godot-dodo project ( https://github.com/minosvasilias/godot-dodo ), which involved finetuning LLaMA models on GitHub-scraped GDScri…

Yes, the changes introduced by Godot 4 were a prime motivator for this project. However, it is not quite as clear cut as OpenAI's models simply being trained on Godot 3.x projects …

The wrapping prompt is also used during inference. ( https://github.com/minosvasilias/godot-dodo/blob/f62b90a4622... ) Prompting like this is useful for instruct-finetunes, and sim…

This repository presents finetuned LLaMA models that try to address the limited ability of existing language models when it comes to generating code for less popular programming la…

Hey HN! This is a pretty straightforward addon for folks that work with GDScript and like to do so within the Godot editor insted of VSCode. Integrating code-completions directly w…