OlegKlimov1337

Maybe it makes sense to start from llama-code, not llama :D I think golang specific model will not be that different from a multi-language model. But it definitely will work better after fine tuning on your code. Check out refact self hosting docker in a couple of days, finetune will be there soon. It will take you 1 GPU and almost no money )

AFAIK There is only one model that do better, it’s phi-1 and it’s python only, and it does not support fill-in-the-middle so you can't really use it.

You can use it in practice, that was the goal of that particular model! It's fast, runs on your own hardware if you want it to.

Yes, it's coming up in a couple of weeks.

I use both from time to time, Copilot surprises with a very good guess maybe twice as often as Refact. (that is subjectively, an opinion) But both help equally well with mechanical work. Hope that helps!