Been playing around with fine-tuning models for specific languages as well (Cloj... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

embedding-shape 6 months ago | parent | context | favorite | on: OpenCode – Open source AI coding agent

Been playing around with fine-tuning models for specific languages as well (Clojure and Rust mostly), but the persistent problem is high quality data sets, mostly I've been generating my own based on my own repositories and chat sessions, what approach are you taking for gathering the data?

numberwan9 6 months ago | [–]

Have you looked on HF? Here's one that is fine tuned on Rust https://huggingface.co/Fortytwo-Network/Strand-Rust-Coder-14...

girvo 6 months ago | [–]

Yeah I have a body of work of 15 years, plus I’ve been building labelled sets from open source (the source code isn’t quite enough on its own)

Now I’m using that to generate synthetic sets and clean it up, but man I’m struggling hah. Fun though.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact