this post was submitted on 22 Feb 2025
15 points (100.0% liked)

Free Open-Source Artificial Intelligence

3255 readers
1 users here now

Welcome to Free Open-Source Artificial Intelligence!

We are a community dedicated to forwarding the availability and access to:

Free Open Source Artificial Intelligence (F.O.S.A.I.)

More AI Communities

LLM Leaderboards

Developer Resources

GitHub Projects

FOSAI Time Capsule

founded 2 years ago
MODERATORS
Blaed@lemmy.world
fosai@lemmy.world
15
Models specialized on only one programming language (piefed.social)
submitted 3 weeks ago by Oskar@piefed.social to c/fosai@lemmy.world
4 comments fedilink hide all child comments
 

There are lots of general-purpose models to use locally, and also coding-specific models.

But are there models specialized in one programming language? My thought was that a model that only needs to handle one language (e.g. Python) could be faster, or be better for a given size.

E.g If I need to code in Rust and is limited to an 8B model to run locally, I was hoping to get better results with a model that is narrower. I don't need it to be able to help with Java.

This approach would of course require switching models, but that's no problem for me.

top 4 comments
sorted by: hot top controversial new old
[–] Yomope@lemmy.ml 2 points 3 weeks ago (1 children)

I’m pretty sure this would not produce better output. Ai has a « thought » of his own.limiting is approach to be pure python won’t offer you the link it can see with a Java approach. With a more diverse knowledge, it can generate a more unique output. Not forcing it to be readable by human may give a more efficient solution. Kinda like compiled code.

[–] Oisteink@feddit.nl 2 points 3 weeks ago

I’d say it depends. Some patterns will be different. Like trying to create zig code when the LLM is trained mostly on javascript and python.

[–] Oskar@piefed.social 1 points 3 weeks ago

I finally found a Python-specific model. Searching is tricky when almost everything around local llms involve Python. https://huggingface.co/codellama/CodeLlama-13b-Python-hf

[–] muntedcrocodile@lemm.ee 1 points 3 weeks ago

I've seen that some exist on huggingface but Idk if they are any better. I would assume if u finetune the model on specific libraries/ur specific codebase then it would be more accurate. If u can run the model locally u can finetune it. Give it a go.