SeacomSrl/SeaPhi3-mini

SeaPhi3-mini is a 4 billion parameter language model developed by Toti Riccardo, fine-tuned from Microsoft's Phi-3-mini-128k-instruct. This model is specifically adapted for Italian language tasks, leveraging a translated dataset for improved performance in Italian contexts. It is designed for applications requiring a compact yet capable model with a 4096-token context length, particularly in Italian-centric natural language processing.