All research
Every paper, release and update, newest first.
7 results
Mario-1: an Italian language model that runs on a CPU
A 0.8-billion-parameter language model built for Italian. It runs on a CPU without a GPU, recognises trick questions, admits what it does not know and does reliable arithmetic.
ResearchResearch
Yeco-PII 2.0
Our new model that finds and hides personal data in text. More accurate than the previous version and better than much larger models, especially in Italian. Every release is digitally signed, so you can verify it is genuine.
ReleaseRelease
Yeco Flash Mini-IT v1
118.1M-parameter Italian micro-LLM, trained for under €15, ~200 tok/s on CPU. Beats Minerva-350M (3× its size) on BoolQ-IT.
PaperPaper
Ender-1
Our AI model for EnderDevelopment, a fine-tune of Qwen2.5-Coder-1.5B (Apache 2.0). It is used only inside the product and is not publicly available.
ReleaseRelease
Yeco-PII v1.0
The first version of our model for finding personal data. It beat larger competitor models on six European languages.
ReleaseRelease
From Standard Italian to Dialects: Early Experiments with Napoletano-Ciro and Piemontese-Gioan
Experimental AI models that speak Neapolitan and Piedmontese, released as open experiments. They are early versions and not part of our main product line.
ResearchResearch
Anti-Loop Layer
A small layer that spots when an AI agent gets stuck in a loop and stops it, in about 12 milliseconds.
SafetySafety