What happens if you train a Romanian LLM on raw public data — an honest experiment

Tue, 22 Sep 2026 14:05:39 +0300

I had some GPUs sitting idle. We’re currently organizing the data for an internal model — slow, careful curation work that doesn’t keep the hardware busy. So I thought: in the meantime, let’s run a test.

Not a serious model. An experiment. I wanted to answer a question I’d been asking myself for a while:

What comes out if you train a Romanian language model from scratch, using only public data, collected from the internet exactly as it is — no careful filtering, no curation, no synthetic data, no human annotation?

Llm on Craciun Florentin Simion

What happens if you train a Romanian LLM on raw public data — an honest experiment