search

minosvasilias / godot-dodo

Finetuning large language models for GDScript generation.
MIT License
523 stars 25 forks source link

Wrong Citation? #3

Closed pplanel closed 1 year ago

pplanel commented 1 year ago

https://github.com/sahil280114/codealpaca

minosvasilias commented 1 year ago

Can you expand on what you mean?

pplanel commented 1 year ago

https://arxiv.org/abs/2212.10560

pplanel commented 1 year ago

This repo is specialization of the referenced paper and repo. You probably should correctly cite the sources of the hard working researchers.

pplanel commented 1 year ago

The godot-dodo project presents a pipeline to finetune open source language models on human-created, language-specific code retrieved from GitHub.

minosvasilias commented 1 year ago

Understood, thank you. I would say the data generation process differs quite significantly from the self-instruct paper, but it's true that stanford-alpaca (which codealpaca seems to be another modification of) has been heavily referenced.

I'll add that to the readme.

minosvasilias commented 1 year ago

Resolved here: https://github.com/minosvasilias/godot-dodo/pull/4