ollama-ui VS godot-dodo

This is great. I was thinking about putting something like this together for personal use, so - thanks for saving us the trouble!

Ollama support would be amazing, especially with the recent integration of codellama and phind-codellama. I’m sure you’re aware, but for the benefit of anyone else: there is a third party Ollama web ui[1] linked to from the ollama project homepage. It’s barebones, but does the trick.

[1]: https://github.com/ollama-ui/ollama-ui

If you can find a large body of good, permissively licensed example code, you can finetune an LLM on it!

There was a similar attempt for Godot script trained a few months ago, and its reportedly pretty good:

https://github.com/minosvasilias/godot-dodo

I think more attempts havent been made because base llama is not that great at coding in general, relative to its other strengths, and stuff like Starcoder has flown under the radar.

This a continuation of previous work done for the godot-dodo project, which involved finetuning LLaMA models on GitHub-scraped GDScript code.

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 GDScript code.

Starcoder performs significantly better than LLaMA using the same dataset, and exceeds evaluation scores of both gpt-4 and gpt-3.5-turbo, showing that single-language finetunes of smaller models may be a competitive option for coding assistants, especially for less commonplace languages such as GDScript.

The twitter thread also details some drawbacks of the current approach, namely increasing occurences where the model references out-of-scope objects in its generated code, a problem that worsens as the amount of training epochs increases.

Not exactly what your looking for, but related: https://github.com/minosvasilias/godot-dodo